© 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. 7288
    Prev
    Next
    INDEX
    Explanations

    content related to news articles, opinions, and reports

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to health and societal issues

    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
    reetings
    -0.75
    avorable
    -0.69
     incent
    -0.61
     endors
    -0.61
     Discussion
    -0.59
     characterization
    -0.58
     Organizations
    -0.56
    xtap
    -0.56
     respondent
    -0.56
     Revised
    -0.56
    POSITIVE LOGITS
    only
    0.90
     civilisation
    0.84
     only
    0.82
    Only
    0.77
     nowhere
    0.75
     cure
    0.75
     ageing
    0.74
     irreversible
    0.72
     instead
    0.68
     never
    0.68
    Activations Density 0.864%

    No Known Activations