© 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. 21335
    Prev
    Next
    INDEX
    Explanations

    verbs indicating understanding, observation, or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of cognitive engagement or attention-oriented 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
    although
    -0.67
    .[
    -0.67
    !.
    -0.66
    +.
    -0.65
    %);
    -0.64
    ibliography
    -0.62
     redes
    -0.62
    Guest
    -0.61
    sometimes
    -0.60
    roxy
    -0.60
    POSITIVE LOGITS
     anything
    1.02
     enough
    0.95
     sufficiently
    0.91
     correctly
    0.87
     any
    0.86
     somebody
    0.83
     something
    0.82
     ANY
    0.81
     your
    0.77
     anymore
    0.76
    Activations Density 0.344%

    No Known Activations