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 Local
    5. 6-RES_SCL-AJT
    6. 45100
    Prev
    Next
    INDEX
    Explanations

    programming code snippets in a specific language

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    525
    +0.05
    0.5%
    553
    +0.04
    0.5%
    147
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    216
    +0.05
    0.07
    230
    +0.04
    0.06
    661
    +0.04
    0.04
    Negative Logits
    £ı
    -0.32
    çīĪ
    -0.32
     Marketable
    -0.30
     compr
    -0.30
    quickShipAvailable
    -0.28
    blem
    -0.27
    ournal
    -0.27
    ãĤ¦ãĤ¹
    -0.27
    ITED
    -0.26
     subpoen
    -0.26
    POSITIVE LOGITS
    roid
    0.39
    static
    0.32
    gravity
    0.30
    AppData
    0.28
    rate
    0.28
    '"
    0.27
    percent
    0.26
    tv
    0.26
    fx
    0.26
    esi
    0.26
    Activations Density 6.716%

    No Known Activations