Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 633
    Prev
    Next
    INDEX
    Explanations

    information about smartphones, devices, and mobile technology

    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
    537
    +0.13
    0.5%
    604
    +0.13
    0.5%
    269
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.07
    343
    +0.13
    0.06
    288
    +0.13
    0.08
    Negative Logits
    tle
    -0.97
    mingham
    -0.94
    pmwiki
    -0.94
    oldemort
    -0.94
    rious
    -0.93
    quist
    -0.89
    bil
    -0.89
    lishes
    -0.89
    roup
    -0.89
     bunk
    -0.88
    POSITIVE LOGITS
     smartphones
    1.06
    Camera
    1.06
    awei
    1.05
     phones
    1.02
     charger
    1.00
    Pixel
    0.98
    phones
    0.98
     apps
    0.96
     cameras
    0.95
     Apps
    0.94
    Activations Density 0.925%

    No Known Activations