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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 11746
    Prev
    Next
    INDEX
    Explanations

    derivatives of the word "sh" followed by another word component

    oai_token-act-pair · gpt-3.5-turbo

    instances of words starting with "sh."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ajax
    -0.75
    anwhile
    -0.65
    OLOGY
    -0.61
    cki
    -0.61
     Leth
    -0.60
     Tone
    -0.59
     ground
    -0.58
     Fargo
    -0.58
     Cosmos
    -0.58
     sax
    -0.57
    POSITIVE LOGITS
    apesh
    1.28
    atters
    1.28
    rapnel
    1.26
    apeshifter
    1.22
    oddy
    1.20
    ackle
    1.20
    ippers
    1.18
    aded
    1.10
    ivers
    1.10
    akedown
    1.09
    Activations Density 0.017%

    No Known Activations