© 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. 7-RES-JB
    11. 8791
    Prev
    Next
    INDEX
    Explanations

    phrases expressing avoidance or refusal

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or intentions to avoid certain actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.86
    ework
    -0.76
    bard
    -0.73
    Kings
    -0.70
     Enhancement
    -0.68
    utical
    -0.68
    icol
    -0.67
    hiba
    -0.66
    strength
    -0.66
    hesis
    -0.65
    POSITIVE LOGITS
     anything
    0.97
     anymore
    0.95
     anybody
    0.94
     anyone
    0.88
     any
    0.83
     nor
    0.80
    reprene
    0.77
     ANY
    0.76
     revenge
    0.74
    ANY
    0.73
    Activations Density 0.040%

    No Known Activations