© 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. 1-RES-JB
    11. 3237
    Prev
    Next
    INDEX
    Explanations

    companies or entities related to technology, specifically those labeled as "Tech 9."

    oai_token-act-pair · gpt-3.5-turbo

    references to technology companies or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.79
     arous
    -0.73
    theless
    -0.68
     CPI
    -0.64
     furthermore
    -0.63
     accompanied
    -0.63
    naire
    -0.63
     captcha
    -0.63
    ``
    -0.62
     refrain
    -0.62
    POSITIVE LOGITS
     Tech
    1.07
    Tech
    1.01
    Crunch
    0.92
    icum
    0.92
    culus
    0.90
    onomy
    0.90
    heastern
    0.90
    elsius
    0.82
    sci
    0.79
    dden
    0.78
    Activations Density 0.007%

    No Known Activations