© 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. 8-RES-JB
    11. 17137
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific symbol or character within the text

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or symbols indicating a sense of constancy or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sussex
    -0.65
     guiActiveUnfocused
    -0.63
    undown
    -0.62
     territorial
    -0.62
     viability
    -0.62
     relevance
    -0.61
     fronts
    -0.60
     ignition
    -0.60
     unsuspecting
    -0.59
     impact
    -0.58
    POSITIVE LOGITS
    ï¸ı
    1.09
    felt
    0.93
    agree
    0.92
    said
    0.88
    know
    0.81
    poke
    0.80
    sand
    0.78
    mand
    0.77
    mir
    0.77
    é¾į
    0.77
    Activations Density 0.152%

    No Known Activations