© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6204
    Prev
    Next
    INDEX
    Explanations

    years and publishers of publications

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to publication and authorship

    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
    vous
    -0.84
    anka
    -0.73
    itiveness
    -0.70
     briefed
    -0.68
     downed
    -0.68
     suited
    -0.67
    rious
    -0.67
    rounded
    -0.67
    iors
    -0.67
    wolves
    -0.66
    POSITIVE LOGITS
     Scrib
    0.89
     commem
    0.82
     conjunction
    0.81
     Springer
    0.80
     paperback
    0.80
     PBS
    0.79
     Spiegel
    0.76
    OUP
    0.71
     tandem
    0.70
     theaters
    0.70
    Activations Density 0.201%

    No Known Activations