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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 395
    Prev
    Next
    INDEX
    Explanations

    financial or legal information, possibly related to medical conditions or news articles

    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
    562
    +0.02
    0.5%
    154
    +0.02
    0.5%
    167
    +0.02
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.02
    0.05
    402
    +0.02
    0.04
    632
    +0.02
    0.03
    Negative Logits
     Advocate
    -0.13
     Typhoon
    -0.12
    FontSize
    -0.11
     Anniversary
    -0.11
    Reilly
    -0.11
    oldown
    -0.11
    Accessory
    -0.11
     represents
    -0.11
     Improvement
    -0.10
     spokesperson
    -0.10
    POSITIVE LOGITS
    warts
    0.15
    eto
    0.14
    rican
    0.13
    rices
    0.13
    atical
    0.13
    ateurs
    0.13
    este
    0.13
    rain
    0.13
    race
    0.12
    rito
    0.12
    Activations Density 0.194%

    No Known Activations