© 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. 10-RES-JB
    11. 11075
    Prev
    Next
    INDEX
    Explanations

    quotes from different individuals

    oai_token-act-pair · gpt-3.5-turbo

    reports or statements attributed to various speakers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨ
    -0.68
    clad
    -0.68
    figure
    -0.66
    Pont
    -0.61
    wed
    -0.60
    WB
    -0.58
    isable
    -0.58
    xtap
    -0.57
    emed
    -0.57
    pees
    -0.57
    POSITIVE LOGITS
     goodbye
    1.06
     hello
    0.95
    =\"
    0.70
    :
    0.68
    Hello
    0.67
     farewell
    0.65
     âĨij
    0.64
     Canaveral
    0.63
    escription
    0.63
    insk
    0.63
    Activations Density 0.047%

    No Known Activations