Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 45095
    Prev
    Next
    INDEX
    Explanations

    instructions or steps in a process

    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
    397
    +0.12
    0.5%
    71
    +0.11
    0.5%
    612
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.12
    0.12
    83
    +0.11
    0.10
    393
    +0.11
    0.26
    Negative Logits
    livious
    -0.80
    OSP
    -0.70
     Debor
    -0.69
    ridor
    -0.68
    ATER
    -0.68
    ahime
    -0.67
    vier
    -0.67
    esome
    -0.66
    Analysis
    -0.66
    odore
    -0.65
    POSITIVE LOGITS
     desired
    0.81
     deems
    0.77
     wished
    0.76
     imaginable
    0.71
    Downloadha
    0.69
     ever
    0.69
     fancy
    0.69
    ifice
    0.69
     deemed
    0.68
     whims
    0.68
    Activations Density 12.128%

    No Known Activations