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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23338
    Prev
    Next
    INDEX
    Explanations

    words related to the sound "sh" being pronounced with emphasis or in connection with various activities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "sh" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.73
     Ajax
    -0.69
     pods
    -0.65
     Tonight
    -0.64
     Codec
    -0.62
     Fargo
    -0.62
     range
    -0.60
     Mub
    -0.60
     Cosmos
    -0.60
     dates
    -0.60
    POSITIVE LOGITS
    apesh
    1.38
    rapnel
    1.37
    oddy
    1.36
    akedown
    1.35
    ivering
    1.32
    unning
    1.28
    ackle
    1.28
    apeshifter
    1.27
    abby
    1.26
    anty
    1.26
    Activations Density 0.014%

    No Known Activations