© 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. 17196
    Prev
    Next
    INDEX
    Explanations

    words related to critical analysis or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    references to critical thinking and its importance in various contexts

    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
    owship
    -0.78
    UAL
    -0.72
    ila
    -0.72
    fred
    -0.70
    boy
    -0.69
    indu
    -0.69
    pered
    -0.68
    Pic
    -0.67
    bows
    -0.67
    ammad
    -0.67
    POSITIVE LOGITS
     faculties
    0.98
     acclaim
    0.96
    ity
    0.94
     mass
    0.88
     jun
    0.88
     appraisal
    0.86
     importance
    0.83
     thinkers
    0.82
     infrastructure
    0.80
     Role
    0.78
    Activations Density 0.033%

    No Known Activations