© 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. 9838
    Prev
    Next
    INDEX
    Explanations

    terms related to specific entities or inventions

    oai_token-act-pair · gpt-3.5-turbo

    nouns and terms related to systems, designs, and creative works

    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
     unfocusedRange
    -0.65
     anytime
    -0.64
    ģ
    -0.63
    ĪĴ
    -0.62
     decreasing
    -0.60
    namese
    -0.58
     cumulative
    -0.58
     Continuing
    -0.57
     idle
    -0.56
    ouple
    -0.55
    POSITIVE LOGITS
     originally
    0.78
     himself
    0.78
    otype
    0.71
     Himself
    0.68
    %]
    0.65
     herself
    0.64
    liest
    0.63
     initially
    0.63
    otypes
    0.63
    çīĪ
    0.62
    Activations Density 0.447%

    No Known Activations