© 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. 8-RES-JB
    11. 5485
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, probably related to news or events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals related to police violence and protests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.78
     Dhabi
    -0.75
     WCS
    -0.69
     Pixie
    -0.69
     capitals
    -0.68
     Governors
    -0.67
     spons
    -0.67
    ournal
    -0.66
    ript
    -0.66
    velength
    -0.65
    POSITIVE LOGITS
     murdered
    1.06
     disappeared
    0.95
     gunned
    0.91
     murder
    0.89
     victims
    0.89
     Jr
    0.88
     disappearance
    0.84
     murdering
    0.84
     Tsarnaev
    0.84
     murderer
    0.83
    Activations Density 0.296%

    No Known Activations