© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 23210
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Ple" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ple" and its variations

    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
     bios
    -0.63
     drift
    -0.60
     appraisal
    -0.59
     FD
    -0.59
    iat
    -0.58
    AUT
    -0.57
     raced
    -0.57
     depreciation
    -0.56
     FSA
    -0.56
     scanners
    -0.55
    POSITIVE LOGITS
    ple
    4.69
    ples
    2.33
    pled
    2.04
    plet
    1.84
    pling
    1.66
    PLE
    1.63
    plets
    1.44
    pletion
    1.41
    ply
    1.37
    plement
    1.35
    Activations Density 0.013%

    No Known Activations