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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 4-RES-JB
    6. 4982
    Prev
    Next
    INDEX
    Explanations

    mentions of residents in a community

    oai_token-act-pair · gpt-3.5-turbo

    mentions of community members or inhabitants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bone
    -0.74
    ãĥ¼ãĥ³
    -0.74
    anche
    -0.73
    MED
    -0.70
    vell
    -0.70
    SourceFile
    -0.69
    Prev
    -0.68
    enegger
    -0.64
    lda
    -0.64
    xon
    -0.64
    POSITIVE LOGITS
    hips
    1.10
    hip
    1.05
    folk
    0.92
     residing
    0.83
     who
    0.75
     residents
    0.75
     Residents
    0.74
    oft
    0.70
     resident
    0.69
     dwell
    0.68
    Activations Density 0.025%

    No Known Activations