© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 13885
    Prev
    Next
    INDEX
    Explanations

    information related to news events or reports

    oai_token-act-pair · gpt-3.5-turbo

    details related to significant events or outcomes in sports and legal contexts

    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
    ecause
    -0.64
     someday
    -0.62
    Zip
    -0.62
     modeled
    -0.61
     willful
    -0.61
     Clintons
    -0.59
     gotten
    -0.59
     disav
    -0.58
     Xer
    -0.57
     DOE
    -0.56
    POSITIVE LOGITS
    ".
    0.88
     organisers
    0.83
    '.
    0.82
    *.
    0.81
     QC
    0.80
    `.
    0.78
    %.
    0.77
     Belfast
    0.76
     organisation
    0.76
    Shape
    0.75
    Activations Density 0.613%

    No Known Activations