© 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. 9-RES-JB
    11. 15421
    Prev
    Next
    INDEX
    Explanations

    numbers and numerical patterns

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shapeshifter
    -0.75
    yre
    -0.71
    gans
    -0.68
    wow
    -0.64
    hip
    -0.63
    ci
    -0.63
    vous
    -0.63
    posed
    -0.63
    edged
    -0.62
    imov
    -0.61
    POSITIVE LOGITS
    Ô
    0.82
     Bleach
    0.65
    --------------------------------------------------------
    0.63
    اÙĦ
    0.62
     à¨
    0.60
    ¯¯¯¯¯¯¯¯
    0.57
     EntityItem
    0.56
    utenberg
    0.55
    galitarian
    0.55
     Remastered
    0.53
    Activations Density 0.067%

    No Known Activations