© 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. 7-RES-JB
    11. 23434
    Prev
    Next
    INDEX
    Explanations

    actions or decisions that are pending or have not yet been finalized

    oai_token-act-pair · gpt-3.5-turbo

    actions related to waiting and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.75
     always
    -0.73
     fasc
    -0.73
     instead
    -0.70
     never
    -0.68
    never
    -0.66
    <?
    -0.64
    rather
    -0.62
     rather
    -0.62
     seldom
    -0.62
    POSITIVE LOGITS
    daq
    0.78
     deadline
    0.75
    pleted
    0.74
    lege
    0.73
    UTE
    0.72
    士
    0.72
     fruition
    0.72
    iphany
    0.71
    ossom
    0.70
     finalized
    0.68
    Activations Density 0.355%

    No Known Activations