© 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. 11-RES-JB
    11. 18727
    Prev
    Next
    INDEX
    Explanations

    numerical and financial terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to acceptance or receiving submissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verty
    -0.81
    raint
    -0.74
    apego
    -0.73
    belt
    -0.71
    itect
    -0.70
    atorium
    -0.69
    rawdownloadcloneembedreportprint
    -0.69
    erity
    -0.68
    terness
    -0.67
    dimension
    -0.64
    POSITIVE LOGITS
     requests
    1.80
     inquiries
    1.64
     queries
    1.56
     emails
    1.51
     calls
    1.50
     invitations
    1.49
     registrations
    1.49
     petitions
    1.49
     applications
    1.47
     referrals
    1.46
    Activations Density 0.385%

    No Known Activations