© 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. 40306
    Prev
    Next
    INDEX
    Explanations

    short descriptive phrases or statements

    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
    0.7%
    408
    +0.11
    0.5%
    122
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    372
    +0.14
    0.13
    711
    +0.11
    0.07
    695
    +0.10
    0.10
    Negative Logits
    steps
    -0.91
    iddles
    -0.86
    hops
    -0.83
    ults
    -0.81
    ATURES
    -0.80
    ateurs
    -0.78
     Surve
    -0.77
    aunts
    -0.74
    tests
    -0.70
    agents
    -0.70
    POSITIVE LOGITS
     tendency
    1.11
     knack
    1.09
     relationship
    1.00
     foothold
    1.00
     amount
    0.98
     penchant
    0.97
     attitude
    0.95
     explanation
    0.93
     inclination
    0.92
     grasp
    0.90
    Activations Density 11.743%

    No Known Activations