© 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. 4376
    Prev
    Next
    INDEX
    Explanations

    technical data or coding elements within the text

    oai_token-act-pair · gpt-3.5-turbo

    specific formatting elements or attributes, likely in a structured document or code context

    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
    istries
    -0.75
    ĺħ
    -0.68
    hement
    -0.68
     forg
    -0.64
    mbuds
    -0.64
     Wasteland
    -0.57
     Correctional
    -0.57
    aldehyde
    -0.57
     GNOME
    -0.56
     separat
    -0.55
    POSITIVE LOGITS
    Zip
    0.89
    Laughs
    0.77
    blank
    0.71
    Shot
    0.71
    Lens
    0.70
    wikipedia
    0.69
    utical
    0.69
    Ger
    0.68
    Bul
    0.67
    NET
    0.66
    Activations Density 0.376%

    No Known Activations