© 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. 15283
    Prev
    Next
    INDEX
    Explanations

    proposals or important decisions

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to proposals, decisions, and significant actions or narratives

    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
    tics
    -0.76
    itudes
    -0.73
    ses
    -0.70
     Machines
    -0.68
     Cups
    -0.67
    etsk
    -0.65
    akia
    -0.65
    hett
    -0.65
     Occupations
    -0.64
    olds
    -0.62
    POSITIVE LOGITS
    atical
    0.82
     standpoint
    0.72
    assian
    0.69
     akin
    0.68
    dylib
    0.66
     called
    0.65
     nonetheless
    0.65
    earance
    0.64
    ulent
    0.64
    Timeout
    0.63
    Activations Density 0.553%

    No Known Activations