© 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. 18749
    Prev
    Next
    INDEX
    Explanations

    adverbs or phrases indicating a consistent or ongoing characteristic or behavior

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating consistency or permanence in preferences or behaviors

    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
    LESS
    -0.76
    channelAvailability
    -0.73
    Sys
    -0.68
     RTX
    -0.65
     Shades
    -0.65
    HQ
    -0.64
    ACTION
    -0.62
    toc
    -0.61
     liner
    -0.59
     Mayhem
    -0.59
    POSITIVE LOGITS
     fascinated
    0.93
     dreamed
    0.93
    ãĤ«
    0.89
     wondered
    0.88
     existed
    0.88
     regarded
    0.87
     assumed
    0.83
     relied
    0.82
     puzzled
    0.80
     worshipped
    0.79
    Activations Density 0.050%

    No Known Activations