© 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. 9956
    Prev
    Next
    INDEX
    Explanations

    words related to hypothetical scenarios or future possibilities

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases involving hypothetical scenarios

    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
     IPM
    -0.74
     Dy
    -0.70
     laced
    -0.68
     lines
    -0.65
     Lawrence
    -0.64
     down
    -0.64
     Dixon
    -0.64
     Trop
    -0.63
     Sandy
    -0.63
     Downs
    -0.63
    POSITIVE LOGITS
    be
    1.55
    have
    1.08
    issue
    1.06
    been
    1.06
    bes
    1.00
    BE
    0.97
    minded
    0.95
    Be
    0.95
    bel
    0.93
    they
    0.93
    Activations Density 0.038%

    No Known Activations