© 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. 4-RES-JB
    11. 7188
    Prev
    Next
    INDEX
    Explanations

    credit notations or attributions in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to credit or citations in a document

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

    No Comments

    Negative Logits
    ²¾
    -0.77
     Lans
    -0.71
     pup
    -0.70
    rooms
    -0.67
    ·
    -0.66
    velt
    -0.66
    vae
    -0.63
    rient
    -0.63
     retard
    -0.63
    rency
    -0.63
    POSITIVE LOGITS
    Credit
    1.08
     Credit
    0.98
     CARD
    0.86
     Cards
    0.85
     Credits
    0.84
    enhagen
    0.79
     credit
    0.78
     Card
    0.78
    credit
    0.76
    card
    0.75
    Activations Density 0.007%

    No Known Activations