© 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. 24560
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations, possibly within a narrative context

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically the closing bracket

    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
    USER
    -0.79
    éŃĶ
    -0.76
    WIN
    -0.68
    athan
    -0.64
     Braves
    -0.63
     vict
    -0.63
    OWS
    -0.63
     Breaker
    -0.62
    WAY
    -0.61
    side
    -0.61
    POSITIVE LOGITS
    zing
    0.91
    htaking
    0.88
    edo
    0.81
    bestos
    0.71
    bley
    0.70
    zed
    0.68
    rote
    0.67
    terday
    0.67
    ylum
    0.65
    hesda
    0.65
    Activations Density 0.000%

    No Known Activations