© 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. 13371
    Prev
    Next
    INDEX
    Explanations

    words related to technological devices

    oai_token-act-pair · gpt-3.5-turbo

    references to hands-on technology and role-playing elements

    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
     Converted
    -0.76
    âĢ¢âĢ¢
    -0.72
     Monstrous
    -0.71
     Sparkle
    -0.69
     Supplemental
    -0.63
     FANTASY
    -0.62
    EStreamFrame
    -0.61
     corro
    -0.60
     typo
    -0.59
    utenberg
    -0.58
    POSITIVE LOGITS
    ages
    0.93
    code
    0.92
    ings
    0.91
    pieces
    0.87
    points
    0.86
    groups
    0.86
    classes
    0.86
    mat
    0.85
    books
    0.84
    book
    0.83
    Activations Density 0.411%

    No Known Activations