© 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. 11-RES-JB
    11. 18814
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and consequences

    oai_token-act-pair · gpt-3.5-turbo

    words associated with violence and aggressive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zbollah
    -0.82
    anguage
    -0.63
    iae
    -0.59
    pora
    -0.59
    ather
    -0.55
    '/
    -0.55
    kie
    -0.52
     condem
    -0.51
    kaya
    -0.51
    schild
    -0.50
    POSITIVE LOGITS
     him
    2.82
    him
    2.06
     HIM
    1.77
     Him
    1.75
     his
    1.62
    his
    1.53
    His
    1.46
    He
    1.39
     he
    1.27
     His
    1.20
    Activations Density 1.004%

    No Known Activations