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

    Neuronpedia

    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. 1267
    Prev
    Next
    INDEX
    Explanations

    phrases related to success or failure in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the effectiveness or failure of actions or strategies

    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
    arth
    -0.74
    umbered
    -0.68
     scanned
    -0.67
    pora
    -0.65
     pont
    -0.64
    inent
    -0.63
    edia
    -0.63
    anamo
    -0.62
    ortment
    -0.62
    udi
    -0.62
    POSITIVE LOGITS
    kok
    0.75
     miser
    0.74
     dividends
    0.70
     synergy
    0.69
     spectacular
    0.69
     disastrous
    0.67
     favor
    0.66
     outcome
    0.66
    better
    0.66
     horribly
    0.65
    Activations Density 0.142%

    No Known Activations