© 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. 8-RES-JB
    11. 17811
    Prev
    Next
    INDEX
    Explanations

    expressions of disagreement and argumentation

    oai_token-act-pair · gpt-3.5-turbo

    claims and statements regarding political or social issues

    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
    OTUS
    -0.78
    Bonus
    -0.71
     Himself
    -0.69
    wn
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
    odiac
    -0.65
    avis
    -0.64
    otion
    -0.64
    alt
    -0.63
    hyde
    -0.63
    POSITIVE LOGITS
     unfair
    1.08
     unfairly
    0.95
     undue
    0.77
     inadequate
    0.76
     misrepresent
    0.75
     misleading
    0.75
     discriminatory
    0.75
     loopholes
    0.74
     threatened
    0.71
     unjust
    0.71
    Activations Density 0.223%

    No Known Activations