© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4633
    Prev
    Next
    INDEX
    Explanations

    phrases that include special characters typically not found in regular English text, most likely related to programming or data formatting

    oai_token-act-pair · gpt-3.5-turbo

    instances of an unusual character or symbol in the text

    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
    worms
    -0.79
     commun
    -0.75
    ieth
    -0.71
    ruck
    -0.68
    aimon
    -0.68
    perate
    -0.67
    ordinate
    -0.66
    erald
    -0.66
    iard
    -0.64
    ides
    -0.64
    POSITIVE LOGITS
    ————————
    1.82
    ————
    1.79
    ————————————————
    1.25
    ——
    1.00
    _-
    0.84
     albeit
    0.81
     namely
    0.76
    especially
    0.73
    feat
    0.73
    albeit
    0.72
    Activations Density 0.119%

    No Known Activations