© 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. 45802
    Prev
    Next
    INDEX
    Explanations

    descriptions of negative societal attitudes towards homosexuality

    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
    +0.35
    1.7%
    393
    +0.16
    0.8%
    481
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.35
    0.30
    393
    +0.16
    0.40
    608
    +0.12
    0.34
    Negative Logits
    ramid
    -0.63
    si
    -0.62
    akening
    -0.59
    ulia
    -0.59
    raviolet
    -0.59
    ndum
    -0.59
    gradation
    -0.58
    rame
    -0.57
    ournal
    -0.57
    acus
    -0.57
    POSITIVE LOGITS
     surprises
    0.89
     interesting
    0.70
     fresh
    0.68
     colorful
    0.67
     goodies
    0.66
     fascinating
    0.66
     curiosity
    0.65
     calories
    0.65
     holes
    0.63
     colourful
    0.63
    Activations Density 17.210%

    No Known Activations