© 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. 3352
    Prev
    Next
    INDEX
    Explanations

    cities or locations

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and related entities

    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
    stem
    -0.96
    WP
    -0.88
    ya
    -0.86
    wal
    -0.85
    ry
    -0.84
    WOR
    -0.83
    rie
    -0.82
    raw
    -0.81
    witch
    -0.79
    RY
    -0.78
    POSITIVE LOGITS
     implication
    0.89
     interruption
    0.81
     eleph
    0.79
     inver
    0.78
     Atom
    0.77
     ASCII
    0.76
     ass
    0.76
     illustration
    0.75
     independents
    0.75
     Insect
    0.75
    Activations Density 0.458%

    No Known Activations