© 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. 33119
    Prev
    Next
    INDEX
    Explanations

    references to dental health, such as teeth, toothbrushes, and dental conditions

    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
    549
    +0.09
    0.5%
    420
    +0.08
    0.5%
    496
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    85
    +0.09
    0.16
    352
    +0.08
    0.16
    240
    +0.07
    0.12
    Negative Logits
    OURCE
    -0.50
    hift
    -0.50
    VD
    -0.48
     Class
    -0.47
     VIDEOS
    -0.46
     posit
    -0.45
    Adds
    -0.45
    OPER
    -0.43
    ersion
    -0.43
     contradictions
    -0.43
    POSITIVE LOGITS
    pick
    0.97
    paste
    0.81
    ache
    0.78
    brush
    0.77
    some
    0.74
    bone
    0.73
    less
    0.68
    shire
    0.65
    stal
    0.64
    hood
    0.63
    Activations Density 9.983%

    No Known Activations