© 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. 8-RES-JB
    11. 9045
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to catastrophic events

    oai_token-act-pair · gpt-3.5-turbo

    words related to apocalyptic or catastrophic events

    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
    chy
    -0.75
    pei
    -0.73
    pton
    -0.73
    pheus
    -0.72
    plet
    -0.72
    yip
    -0.70
    hov
    -0.69
    skirts
    -0.68
    ettings
    -0.68
    plets
    -0.67
    POSITIVE LOGITS
    rophe
    1.24
    rophic
    1.09
    roph
    0.91
    efully
    0.89
    eful
    0.88
    ream
    0.88
    ruct
    0.88
    igmat
    0.87
    rike
    0.86
    rop
    0.85
    Activations Density 0.044%

    No Known Activations