© 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. 6-RES-JB
    11. 4985
    Prev
    Next
    INDEX
    Explanations

    statements of belief or persuasion

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political or societal beliefs and assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     partName
    -0.66
    EMS
    -0.60
    Attempts
    -0.60
     sqor
    -0.56
    geoning
    -0.56
    mentioned
    -0.54
    assuming
    -0.54
     largeDownload
    -0.54
     sidx
    -0.52
    iHUD
    -0.51
    POSITIVE LOGITS
     immoral
    0.72
     somehow
    0.69
     daddy
    0.67
     someday
    0.67
     rapists
    0.66
     raping
    0.63
     pedoph
    0.62
     homosexuals
    0.62
     ruining
    0.62
     "'
    0.61
    Activations Density 1.079%

    No Known Activations