© 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. 23748
    Prev
    Next
    INDEX
    Explanations

    official representatives or spokespersons mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    references to spokespersons or representatives

    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
    bows
    -0.81
    Dick
    -0.68
    APTER
    -0.66
    TIT
    -0.65
    veyard
    -0.65
    SPONSORED
    -0.64
    Textures
    -0.63
    rums
    -0.62
    CHAPTER
    -0.62
    Winner
    -0.61
    POSITIVE LOGITS
     spokesperson
    0.76
    rolet
    0.76
    alyst
    0.75
     affiliated
    0.71
     representative
    0.71
     spokeswoman
    0.70
     of
    0.70
    hetical
    0.69
    onse
    0.67
     thereof
    0.67
    Activations Density 0.181%

    No Known Activations