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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 18129
    Prev
    Next
    INDEX
    Explanations

    words related to identification or categorization

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "identify"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orld
    -0.82
    imeo
    -0.76
    bare
    -0.74
    perty
    -0.71
     raining
    -0.70
    uden
    -0.69
    uss
    -0.67
     beating
    -0.66
     rejoice
    -0.65
    nuts
    -0.65
    POSITIVE LOGITS
    ãĤ©
    0.94
     identifies
    0.84
     Identification
    0.84
    identified
    0.82
     identification
    0.80
     identifiers
    0.79
     Ident
    0.78
     IDs
    0.77
     identifying
    0.75
    ãĤ¿
    0.75
    Activations Density 0.029%

    No Known Activations