© 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. 4069
    Prev
    Next
    INDEX
    Explanations

    phrases describing different types or categories

    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
    +0.15
    0.6%
    44
    +0.11
    0.4%
    195
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.15
    0.22
    6
    +0.11
    0.14
    375
    +0.11
    0.06
    Negative Logits
    romeda
    -0.81
     Rings
    -0.81
    umbai
    -0.79
    姫
    -0.78
    pload
    -0.76
    olulu
    -0.76
     Bots
    -0.75
     destro
    -0.75
    nuts
    -0.74
    iae
    -0.73
    POSITIVE LOGITS
    face
    1.49
    faces
    1.44
    etter
    1.19
    etting
    1.15
    casting
    1.07
    ahead
    1.02
    cast
    0.89
    classes
    0.89
    alias
    0.84
    typ
    0.83
    Activations Density 10.631%

    No Known Activations