Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 24380
    Prev
    Next
    INDEX
    Explanations

    terms related to election processes such as "canvassing," "ballots," and "recount."

    oai_token-act-pair · gpt-3.5-turbo

    references to ballots and canvassing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vid
    -0.83
    LU
    -0.76
    mund
    -0.72
     Odyssey
    -0.68
    éĥ
    -0.65
    Dialogue
    -0.65
    AE
    -0.63
    Fail
    -0.62
    ä¹
    -0.61
    nesses
    -0.60
    POSITIVE LOGITS
     canv
    1.13
    asing
    0.92
    assing
    0.90
    bsite
    0.90
    atform
    0.90
     leaflets
    0.89
    ases
    0.85
    iries
    0.82
    asers
    0.82
    issors
    0.81
    Activations Density 0.041%

    No Known Activations