© 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. 8-RES-JB
    11. 5090
    Prev
    Next
    INDEX
    Explanations

    actions related to setting out on a journey or mission

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a purpose or intention behind actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reopened
    -0.68
     suppressed
    -0.65
     coh
    -0.64
     closed
    -0.64
    outer
    -0.63
     outage
    -0.61
     tense
    -0.60
     wrap
    -0.60
     upkeep
    -0.58
     asset
    -0.58
    POSITIVE LOGITS
    fitted
    0.81
    AAF
    0.80
    posts
    0.73
    sonian
    0.72
     anew
    0.72
    ngth
    0.70
    ¯¯¯¯¯¯¯¯
    0.70
     Seeking
    0.69
    gow
    0.69
    RAG
    0.68
    Activations Density 0.037%

    No Known Activations