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

    Neuronpedia

    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. 9905
    Prev
    Next
    INDEX
    Explanations

    web URLs

    oai_token-act-pair · gpt-3.5-turbo

    repeated web links or URLs

    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
     Lowell
    -0.66
     bases
    -0.62
     deficiencies
    -0.61
     Alexandria
    -0.59
     representation
    -0.58
     renovation
    -0.57
     Prohibition
    -0.56
     ageing
    -0.56
     Camden
    -0.55
    rament
    -0.54
    POSITIVE LOGITS
    cdn
    0.80
    ffee
    0.77
    gh
    0.75
    à
    0.75
    ffe
    0.73
    ciating
    0.71
    verage
    0.71
    ck
    0.69
    amn
    0.69
    000000
    0.68
    Activations Density 0.010%

    No Known Activations