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. 0-RES-JB
    6. 9101
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Hamm"

    oai_token-act-pair · gpt-3.5-turbo

    references to ‘amm’ or related names

    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
     slice
    -0.69
     constrained
    -0.68
     Chip
    -0.68
     turnaround
    -0.67
     slate
    -0.67
     fade
    -0.64
     downgrade
    -0.63
     snap
    -0.62
     meet
    -0.62
     Renaissance
    -0.62
    POSITIVE LOGITS
    amm
    4.38
    ammed
    1.65
    ammers
    1.55
    ams
    1.53
    amb
    1.34
    lamm
    1.25
    amin
    1.18
     Hamm
    1.16
    ami
    1.14
    imm
    1.14
    Activations Density 0.009%

    No Known Activations