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. 6989
    Prev
    Next
    INDEX
    Explanations

    mentions of "aster" in words

    oai_token-act-pair · gpt-3.5-turbo

    words related to amusement and entertainment, particularly focusing on roller coasters

    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
     Question
    -0.63
     li
    -0.61
     NH
    -0.61
     Clause
    -0.60
     Nep
    -0.60
     Ng
    -0.60
     wa
    -0.59
     clauses
    -0.59
     dressing
    -0.59
     NP
    -0.59
    POSITIVE LOGITS
    aster
    4.85
    asters
    3.41
    asting
    1.93
    asts
    1.76
    AST
    1.75
    ast
    1.59
    asted
    1.57
    asta
    1.51
    astered
    1.50
    astery
    1.48
    Activations Density 0.010%

    No Known Activations