© 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. 13823
    Prev
    Next
    INDEX
    Explanations

    power-related terms and phrases, particularly related to control and settings adjustments

    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
    +0.14
    0.8%
    288
    +0.11
    0.7%
    218
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.14
    0.13
    255
    +0.11
    0.07
    249
    +0.11
    0.06
    Negative Logits
     Chrys
    -0.53
    Intel
    -0.53
    Eth
    -0.52
    tein
    -0.52
    Bi
    -0.52
    iscopal
    -0.51
    LY
    -0.51
    anthrop
    -0.51
    cale
    -0.51
    ophile
    -0.50
    POSITIVE LOGITS
     valve
    0.65
    taker
    0.64
     mechanisms
    0.61
     valves
    0.61
    ptives
    0.59
     exercised
    0.59
    cuts
    0.59
    rollers
    0.59
    ption
    0.58
    ulators
    0.58
    Activations Density 6.748%

    No Known Activations