© 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. 21349
    Prev
    Next
    INDEX
    Explanations

    terms related to policies and regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to policy discussions or legislative matters

    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
     reckoned
    -0.77
     snapped
    -0.76
    odiac
    -0.75
    digy
    -0.73
     (£
    -0.69
    mania
    -0.69
    Legend
    -0.69
     cubic
    -0.68
     hooked
    -0.66
    ãĥĺ
    -0.65
    POSITIVE LOGITS
     harms
    1.11
     discriminatory
    1.11
     DOJ
    1.11
     unethical
    1.09
     DMCA
    1.09
     unconstitutional
    1.07
     advocacy
    1.07
     defamation
    1.04
     ACLU
    1.04
     FTC
    1.04
    Activations Density 0.852%

    No Known Activations