© 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. 9952
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Sanders."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political figures and events

    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
    gling
    -0.56
     (#
    -0.55
    itar
    -0.53
    leigh
    -0.53
     Mechanical
    -0.52
     LR
    -0.52
    usercontent
    -0.51
     Mons
    -0.51
    chers
    -0.50
    sth
    -0.50
    POSITIVE LOGITS
     explodes
    0.53
    accompan
    0.52
    =]
    0.50
     blister
    0.50
     accuser
    0.50
    ccording
    0.50
    Charges
    0.49
     rejects
    0.49
    ]);
    0.49
     slams
    0.49
    Activations Density 0.030%

    No Known Activations