© 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. 7474
    Prev
    Next
    INDEX
    Explanations

    the verb 'find' followed by different scenarios or objects

    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
    403
    +0.16
    0.6%
    123
    +0.15
    0.5%
    435
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.16
    0.09
    183
    +0.15
    0.07
    411
    +0.13
    0.06
    Negative Logits
    mun
    -1.01
    wr
    -0.97
    mind
    -0.95
    shield
    -0.93
    isc
    -0.93
    jab
    -0.90
    itational
    -0.90
    sis
    -0.89
    cancer
    -0.89
    pac
    -0.88
    POSITIVE LOGITS
     plenty
    1.24
     ample
    1.13
    enance
    1.09
     parallels
    1.08
     ANY
    0.99
    owan
    0.98
     lots
    0.95
     WHERE
    0.94
     yourself
    0.94
     glimps
    0.94
    Activations Density 1.367%

    No Known Activations