© 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. 6-RES-JB
    11. 20306
    Prev
    Next
    INDEX
    Explanations

    words related to cues and signals

    oai_token-act-pair · gpt-3.5-turbo

    references to visual and contextual cues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oslav
    -0.86
    rior
    -0.77
    ategory
    -0.77
    sburgh
    -0.72
    owed
    -0.71
    atism
    -0.68
    ofi
    -0.67
     Seym
    -0.65
    zai
    -0.65
    zl
    -0.65
    POSITIVE LOGITS
     cue
    0.94
     clue
    0.86
     clues
    0.77
    vine
    0.75
     hint
    0.73
     cues
    0.73
    DragonMagazine
    0.71
    tale
    0.70
     handler
    0.69
     glean
    0.69
    Activations Density 0.029%

    No Known Activations