© 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. 9924
    Prev
    Next
    INDEX
    Explanations

    phrases indicating impossibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating impossibility or lack of options

    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
     streng
    -0.81
    rongh
    -0.76
    asts
    -0.71
    ahime
    -0.69
    xon
    -0.69
    zbollah
    -0.67
    inion
    -0.67
    eals
    -0.67
    notations
    -0.67
    gments
    -0.65
    POSITIVE LOGITS
     whatsoever
    1.12
     anybody
    1.06
     anyone
    1.01
     around
    0.91
     else
    0.86
     anymore
    0.84
     anywhere
    0.82
     anything
    0.80
     somebody
    0.77
     you
    0.77
    Activations Density 0.060%

    No Known Activations