© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4993
    Prev
    Next
    INDEX
    Explanations

    conflicts of interest mentioned in text

    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
    393
    +0.07
    0.5%
    12
    +0.07
    0.5%
    570
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.07
    0.23
    393
    +0.07
    0.34
    385
    +0.06
    0.25
    Negative Logits
    STER
    -0.49
    uries
    -0.44
    chester
    -0.43
    uristic
    -0.43
    NPR
    -0.42
    reys
    -0.40
    Mill
    -0.40
    vernment
    -0.40
     Jelly
    -0.40
    nz
    -0.38
    POSITIVE LOGITS
     interest
    0.45
    interest
    0.43
     Interest
    0.42
     sexes
    0.41
    rimination
    0.41
    between
    0.40
     sorts
    0.40
    course
    0.39
     course
    0.39
    ouple
    0.39
    Activations Density 13.825%

    No Known Activations