© 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. 4203
    Prev
    Next
    INDEX
    Explanations

    mentions of "most" related to quantitative evaluations

    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
    +0.24
    0.9%
    393
    +0.18
    0.7%
    726
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.24
    0.33
    393
    +0.18
    0.29
    598
    +0.16
    0.10
    Negative Logits
    rompt
    -0.85
    vest
    -0.83
    icer
    -0.79
    heid
    -0.79
    pload
    -0.79
     Mellon
    -0.76
    instead
    -0.75
    alid
    -0.72
    adium
    -0.70
    thur
    -0.70
    POSITIVE LOGITS
     importantly
    1.35
    afa
    0.96
     notably
    0.96
    body
    0.93
    rar
    0.92
     important
    0.89
    likely
    0.88
     likely
    0.86
     observers
    0.85
     egreg
    0.83
    Activations Density 13.629%

    No Known Activations