© 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
    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. 45788
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical movement or relocation

    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
    +0.23
    0.9%
    665
    +0.12
    0.5%
    642
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    349
    +0.23
    0.06
    665
    +0.12
    0.12
    70
    +0.12
    0.10
    Negative Logits
    oured
    -0.79
    oys
    -0.79
    omial
    -0.77
    iciency
    -0.76
    sung
    -0.75
    lain
    -0.74
    inges
    -0.72
    ouring
    -0.71
    conn
    -0.68
    vous
    -0.66
    POSITIVE LOGITS
     forward
    1.05
     toward
    1.01
     towards
    0.96
     away
    0.90
    objects
    0.83
     swiftly
    0.82
    brates
    0.82
    Motion
    0.82
     Forward
    0.81
     into
    0.77
    Activations Density 7.404%

    No Known Activations