© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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 Local
    9. 6-RES_SCL-AJT
    11. 34806
    Prev
    Next
    INDEX
    Explanations

    phrases related to vertical or top-down orientation

    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
    447
    +0.12
    0.6%
    99
    +0.10
    0.5%
    262
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.12
    0.06
    393
    +0.10
    0.26
    77
    +0.10
    0.08
    Negative Logits
    ushes
    -0.71
    ...]
    -0.62
    KING
    -0.61
    arag
    -0.60
    ushima
    -0.58
    thy
    -0.58
    ugh
    -0.58
    english
    -0.57
    May
    -0.56
    amoto
    -0.56
    POSITIVE LOGITS
    stairs
    0.75
     version
    0.70
     versions
    0.70
    stock
    0.63
    spin
    0.62
     paddle
    0.61
    stretched
    0.59
     syndrome
    0.59
     overlay
    0.58
     cart
    0.57
    Activations Density 12.274%

    No Known Activations