© 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. 2-RES-JB
    11. 397
    Prev
    Next
    INDEX
    Explanations

    the word "Jackson"

    oai_token-act-pair · gpt-4-turbo

    references to a specific location - Jackson

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Jackson."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lator
    -0.78
    htaking
    -0.75
    ancial
    -0.74
    ĻĤ
    -0.74
    VOL
    -0.72
    TPS
    -0.70
    jad
    -0.70
    INAL
    -0.68
    spread
    -0.67
    available
    -0.67
    POSITIVE LOGITS
     Hole
    0.97
     Jackson
    0.93
    SON
    0.80
    ston
    0.76
     Browne
    0.72
    angel
    0.72
    inson
    0.71
    hurst
    0.71
    owa
    0.70
    Jackson
    0.69
    Activations Density 0.007%

    No Known Activations