© 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. 9892
    Prev
    Next
    INDEX
    Explanations

    mentions of medical conditions or symptoms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "out" or "being out," especially 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
    ha
    -0.85
    Gra
    -0.82
    leigh
    -0.81
    gra
    -0.81
    hei
    -0.75
    angle
    -0.73
     helic
    -0.72
    lia
    -0.72
    hene
    -0.70
    ŃĶ
    -0.70
    POSITIVE LOGITS
     Out
    1.99
    Out
    1.89
     OUT
    1.83
    out
    1.80
     out
    1.72
    OUT
    1.71
     outs
    1.51
    outs
    1.51
     Outs
    1.41
    outed
    1.15
    Activations Density 0.110%

    No Known Activations