© 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. 10-RES-JB
    11. 22193
    Prev
    Next
    INDEX
    Explanations

    aggressive actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    actions related to violence and sexual assault

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IJ
    -0.66
    dra
    -0.63
    ERT
    -0.62
    gat
    -0.61
    hower
    -0.60
     GOODMAN
    -0.59
    £ı
    -0.59
    ©¶æ¥µ
    -0.58
     adversary
    -0.57
    assador
    -0.57
    POSITIVE LOGITS
     us
    1.20
     me
    1.09
     them
    1.05
     you
    0.99
     yours
    0.89
     him
    0.88
    you
    0.85
     your
    0.84
     hers
    0.82
     theirs
    0.81
    Activations Density 0.531%

    No Known Activations