© 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. 9-RES-JB
    11. 4610
    Prev
    Next
    INDEX
    Explanations

    links or references to URLs

    oai_token-act-pair · gpt-3.5-turbo

    elements related to technical specifications and quantitative details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÂŃ
    -0.84
    Enlarge
    -0.79
    toggle
    -0.63
     Adolf
    -0.59
    uble
    -0.58
     Canaver
    -0.56
    ÂŃ
    -0.54
    ½
    -0.53
    chanted
    -0.53
    century
    -0.53
    POSITIVE LOGITS
     thru
    0.81
     independ
    0.78
     devs
    0.75
     CoC
    0.75
     alot
    0.74
     doesnt
    0.74
     didnt
    0.74
     tho
    0.73
     aforementioned
    0.70
     dont
    0.69
    Activations Density 1.875%

    No Known Activations