© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 17052
    Prev
    Next
    INDEX
    Explanations

    hyperlinks to images

    oai_token-act-pair · gpt-3.5-turbo

    references to images

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

    No Comments

    Negative Logits
    cffff
    -0.72
    edient
    -0.69
     administ
    -0.68
    NetMessage
    -0.63
     Leilan
    -0.61
    ifted
    -0.61
    Ļ½
    -0.60
    quartered
    -0.60
     trave
    -0.60
     Dew
    -0.59
    POSITIVE LOGITS
    colo
    0.97
    amera
    0.92
     pic
    0.88
    ://
    0.86
     pics
    0.82
    ares
    0.80
    Pic
    0.79
    chrom
    0.79
    pic
    0.78
    twitter
    0.78
    Activations Density 0.008%

    No Known Activations