© 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 EvalsExportsinterp-engineNEWAPI 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. 2218
    Prev
    Next
    INDEX
    Explanations

    locations and directions mentioned in a text

    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
    247
    +0.15
    0.6%
    565
    +0.14
    0.5%
    323
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    654
    +0.15
    0.06
    323
    +0.14
    0.07
    327
    +0.14
    0.07
    Negative Logits
    rix
    -0.94
    uci
    -0.90
    seed
    -0.90
    ibr
    -0.87
    nation
    -0.87
    hement
    -0.85
    orian
    -0.84
     Flavoring
    -0.84
    peat
    -0.82
    OY
    -0.81
    POSITIVE LOGITS
     entrances
    1.22
     vicinity
    1.13
     nearest
    1.07
     entrance
    1.04
     adjacent
    0.96
     nearby
    0.94
     occupied
    0.92
     corner
    0.91
     periphery
    0.90
     perimeter
    0.90
    Activations Density 1.402%

    No Known Activations