© 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. 7-RES-JB
    11. 1969
    Prev
    Next
    INDEX
    Explanations

    informational phrases related to news updates and features

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and references to additional information or related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.78
    erity
    -0.75
    agall
    -0.75
    gdala
    -0.75
    amia
    -0.74
    llan
    -0.73
    gado
    -0.73
    gypt
    -0.71
    wreck
    -0.70
    auga
    -0.70
    POSITIVE LOGITS
     info
    1.08
     previews
    1.01
     reviews
    1.00
     specifications
    0.99
     updates
    0.98
     adv
    0.97
     informational
    0.95
     presentations
    0.94
     corrections
    0.94
     announcements
    0.94
    Activations Density 0.332%

    No Known Activations