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. 0-RES-JB
    6. 3271
    Prev
    Next
    INDEX
    Explanations

    words related to qualities or concepts that end in "icity"

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to various forms of "icity."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hook
    -0.80
     Hudson
    -0.75
    hook
    -0.71
    ockey
    -0.71
    CPU
    -0.70
    affer
    -0.66
     Revel
    -0.65
    ooks
    -0.64
    vich
    -0.64
     bracket
    -0.63
    POSITIVE LOGITS
    icity
    1.88
    cia
    1.83
    edia
    1.66
    meaning
    1.63
    essa
    1.18
    entimes
    1.16
    tera
    1.14
     Rossi
    1.04
    eli
    1.03
    esa
    1.02
    Activations Density 0.049%

    No Known Activations