© 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. 4-RES-JB
    11. 408
    Prev
    Next
    INDEX
    Explanations

    HTML tags used in webpage design

    oai_token-act-pair · gpt-3.5-turbo

    HTML tag-related syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.83
    İĭ
    -0.80
    ĪĴ
    -0.77
    ģ«
    -0.73
     unsolved
    -0.71
    cius
    -0.71
    ĵĺ
    -0.70
    aido
    -0.70
    xon
    -0.69
     whist
    -0.68
    POSITIVE LOGITS
     <!--
    1.02
    )</
    0.90
    "},{"
    0.84
    =>
    0.84
     <
    0.82
    âĸij
    0.82
    ">
    0.81
    âĸĴ
    0.81
    TPS
    0.79
    PIN
    0.77
    Activations Density 0.007%

    No Known Activations