© 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. 7-RES-JB
    11. 16729
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals and their statements or actions

    oai_token-act-pair · gpt-3.5-turbo

    statements or quotes from discussions involving political figures or events

    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
     upstream
    -0.89
     downstream
    -0.74
    icter
    -0.71
    aceae
    -0.69
     LTD
    -0.67
    emis
    -0.67
     lantern
    -0.67
     accelerator
    -0.65
     fingerprint
    -0.65
     duplication
    -0.65
    POSITIVE LOGITS
    SPONSORED
    1.42
    Asked
    1.35
    Speaking
    1.26
    Refer
    1.20
    Calling
    1.09
    Talking
    1.06
    Republicans
    1.04
    ADVERTISEMENT
    1.03
    Critics
    1.00
    President
    0.99
    Activations Density 0.485%

    No Known Activations