© 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. 8-RES-JB
    11. 8606
    Prev
    Next
    INDEX
    Explanations

    phrases or names related to the Adirondacks

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ir"

    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
    ļé
    -0.63
     untreated
    -0.63
     Unch
    -0.61
    er
    -0.60
    reme
    -0.59
    raised
    -0.59
    Ĥª
    -0.59
    Ĥ¬
    -0.58
    YC
    -0.58
     CLSID
    -0.57
    POSITIVE LOGITS
    vana
    1.36
    ROR
    1.06
    rha
    1.04
    andom
    1.04
    mingham
    0.94
    ror
    0.91
    bid
    0.89
    cles
    0.86
    rh
    0.83
    acial
    0.82
    Activations Density 0.031%

    No Known Activations