© 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. 11-RES-JB
    11. 17157
    Prev
    Next
    INDEX
    Explanations

    sentences indicating the importance of certain factors for a positive outcome or resolution

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding social responsibility and the consequences of inaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ancock
    -0.65
    elight
    -0.64
    Favorite
    -0.63
     refreshed
    -0.63
    FTWARE
    -0.62
     GOODMAN
    -0.61
    yip
    -0.60
    Latest
    -0.59
     remem
    -0.59
     Precision
    -0.59
    POSITIVE LOGITS
     doomed
    0.96
     starve
    0.93
     spiral
    0.90
     stagn
    0.89
     deterior
    0.89
     risk
    0.87
     harm
    0.86
     collapse
    0.86
     unsustainable
    0.86
     collapses
    0.85
    Activations Density 0.303%

    No Known Activations