© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12252
    Prev
    Next
    INDEX
    Explanations

    locations mentioned in the text - particularly focusing on the state of Texas or events happening in Texas

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    127
    +0.15
    0.5%
    535
    +0.13
    0.5%
    459
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.10
    65
    +0.13
    0.07
    224
    +0.13
    0.07
    Negative Logits
    theless
    -1.32
    ufact
    -1.01
    onymous
    -0.93
    fman
    -0.93
    iatrics
    -0.93
     captcha
    -0.93
    lihood
    -0.93
    ãĥĭ
    -0.91
    etheless
    -0.90
    */(
    -0.89
    POSITIVE LOGITS
     Instruments
    1.34
     Rangers
    1.16
     Chronicle
    1.14
     Texans
    1.10
     Tribune
    1.09
    burg
    1.08
     Tech
    1.05
    ns
    1.05
    Stars
    1.02
     Longh
    1.01
    Activations Density 1.791%

    No Known Activations