© 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. 11-RES-JB
    11. 5149
    Prev
    Next
    INDEX
    Explanations

    phrases related to political actions and decisions

    oai_token-act-pair · gpt-3.5-turbo

    multiple clauses or phrases that indicate actions or regulations

    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
    ãĥ¼ãĥĨãĤ£
    -0.74
    =-=-=-=-=-=-=-=-
    -0.68
    ileged
    -0.68
    ãģł
    -0.66
    enne
    -0.66
    hedon
    -0.66
    sylv
    -0.65
    emporary
    -0.65
    mouth
    -0.64
    REDACTED
    -0.64
    POSITIVE LOGITS
     citing
    1.18
     paving
    1.11
     arguing
    1.11
     saying
    1.07
     reversing
    1.01
     prompting
    1.00
     fearing
    0.99
     sparking
    0.98
     prohibiting
    0.97
     rejecting
    0.96
    Activations Density 0.312%

    No Known Activations