© 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. 40001
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and disputes

    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
    710
    +0.12
    0.6%
    57
    +0.10
    0.5%
    585
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.18
    288
    +0.10
    0.18
    57
    +0.09
    0.06
    Negative Logits
    RED
    -0.64
    é¾
    -0.56
    ulia
    -0.56
     Diversity
    -0.55
     aval
    -0.54
     elig
    -0.54
    RN
    -0.53
     extrater
    -0.53
     variance
    -0.53
     Demand
    -0.51
    POSITIVE LOGITS
     Whitman
    0.96
     Disney
    0.89
    rip
    0.85
    zing
    0.81
    enthal
    0.75
    zman
    0.73
     Walt
    0.73
    ter
    0.73
    zes
    0.71
    pins
    0.70
    Activations Density 4.941%

    No Known Activations