© 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. 3-RES-JB
    11. 23894
    Prev
    Next
    INDEX
    Explanations

    words related to specific names or locations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and notable entities

    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
     respectively
    -0.61
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.59
    ĵĺ
    -0.55
     ..."
    -0.55
     opposite
    -0.55
     trans
    -0.54
     ...
    -0.54
     prec
    -0.53
     etc
    -0.52
     seminal
    -0.51
    POSITIVE LOGITS
    ogether
    0.88
    resa
    0.84
    anyahu
    0.83
    vertising
    0.83
    jamin
    0.83
    xiety
    0.81
    withstanding
    0.79
    agascar
    0.77
    odore
    0.76
    tenance
    0.74
    Activations Density 0.603%

    No Known Activations