© 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. 10202
    Prev
    Next
    INDEX
    Explanations

    terms related to social or political activism

    oai_token-act-pair · gpt-3.5-turbo

    references to social movements and collective 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
     Recent
    -0.64
    erning
    -0.63
    amiliar
    -0.63
    utics
    -0.61
     particulars
    -0.61
    addle
    -0.59
    serving
    -0.58
     distinctive
    -0.57
    odic
    -0.57
    doms
    -0.55
    POSITIVE LOGITS
     didnt
    1.60
     pretended
    1.21
     pissed
    1.18
     forgot
    1.18
     screamed
    1.17
     lied
    1.16
     messed
    1.16
     decided
    1.14
     blew
    1.13
     cheated
    1.13
    Activations Density 0.610%

    No Known Activations