© 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. 3-RES-JB
    11. 692
    Prev
    Next
    INDEX
    Explanations

    sequences related to voting in a ranking or poll context

    oai_token-act-pair · gpt-3.5-turbo

    references to votes or rankings

    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
    omorphic
    -0.58
    yout
    -0.57
     favor
    -0.52
    conom
    -0.52
    ãĥķãĤ©
    -0.51
     coh
    -0.51
    Reloaded
    -0.50
    nen
    -0.48
     fences
    -0.47
    20439
    -0.46
    POSITIVE LOGITS
    onga
    0.52
     TBD
    0.50
     TBA
    0.46
    ucer
    0.46
     Valkyrie
    0.45
     Ibid
    0.45
    hovah
    0.45
     Extras
    0.45
    endif
    0.44
     Destination
    0.44
    Activations Density 0.746%

    No Known Activations