© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4158
    Prev
    Next
    INDEX
    Explanations

    phrases related to tasks or responsibilities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "do" and its variations, indicating tasks and actions that need attention or completion

    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
    CHAT
    -0.83
    rets
    -0.72
    Used
    -0.69
    furt
    -0.65
    pered
    -0.65
    irl
    -0.64
    rin
    -0.64
    ogly
    -0.61
    BuyableInstoreAndOnline
    -0.60
    ricted
    -0.60
    POSITIVE LOGITS
     domestically
    0.84
    uate
    0.82
     administr
    0.82
     academ
    0.77
     collabor
    0.74
     educating
    0.74
     regarding
    0.73
    atives
    0.72
     creatively
    0.71
     locally
    0.69
    Activations Density 0.100%

    No Known Activations