© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 14738
    Prev
    Next
    INDEX
    Explanations

    mentions of involvement or participation in various activities or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "involved" in various contexts

    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
    mares
    -0.76
    OIL
    -0.74
    ppel
    -0.71
    efully
    -0.69
    Jet
    -0.68
    ipe
    -0.66
    edes
    -0.64
    haar
    -0.64
    \\\\\\\\
    -0.61
    ãĥ©ãĥ³
    -0.61
    POSITIVE LOGITS
    ioned
    0.84
     involved
    0.81
    itaire
    0.76
    enza
    0.74
    olved
    0.73
    ulkan
    0.69
     implicated
    0.69
    involved
    0.66
    Offline
    0.66
    ive
    0.66
    Activations Density 0.023%

    No Known Activations