© 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. 3-RES-JB
    11. 122
    Prev
    Next
    INDEX
    Explanations

    names of locations, possibly focusing on state abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the state of Kentucky and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -1.00
    mort
    -0.92
    enberg
    -0.74
    ered
    -0.74
    icy
    -0.74
    ending
    -0.71
    err
    -0.71
    caps
    -0.70
    heim
    -0.68
    specified
    -0.68
    POSITIVE LOGITS
    KY
    0.85
     Pradesh
    0.84
     KY
    0.82
    VO
    0.81
    FU
    0.80
    NECT
    0.75
    WT
    0.74
    LLOW
    0.73
    KE
    0.71
    EVA
    0.71
    Activations Density 0.025%

    No Known Activations