© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 15920
    Prev
    Next
    INDEX
    Explanations

    words related to ways of accessing information or resources

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data access and connectivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abst
    -0.66
     sperm
    -0.62
     disband
    -0.61
     circling
    -0.60
    tif
    -0.60
     scra
    -0.59
    hari
    -0.59
     ejac
    -0.59
    annis
    -0.59
     Kern
    -0.58
    POSITIVE LOGITS
    ibility
    1.33
    ibly
    1.14
    ibl
    1.00
    ible
    0.97
     privileges
    0.92
    ibles
    0.87
    acion
    0.86
    ãĥ¼ãĥĨ
    0.86
    ioned
    0.84
    IBLE
    0.84
    Activations Density 0.017%

    No Known Activations