© 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. 20351
    Prev
    Next
    INDEX
    Explanations

    actions taken by groups of people in response to events or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to public protests or collective actions

    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
    thood
    -0.81
    ainment
    -0.72
    hin
    -0.66
    odan
    -0.64
     matured
    -0.63
    nown
    -0.63
    Prosecut
    -0.63
    ãĥīãĥ©ãĤ´ãĥ³
    -0.62
    ulhu
    -0.61
    division
    -0.60
    POSITIVE LOGITS
     clam
    1.01
     petitions
    0.97
     boycot
    0.91
     ballots
    0.91
     selfies
    0.89
     candles
    0.87
     applaud
    0.85
     boycott
    0.85
     chants
    0.83
     queues
    0.81
    Activations Density 0.454%

    No Known Activations