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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19404
    Prev
    Next
    INDEX
    Explanations

    adjectives and phrases related to acceptability or approval

    oai_token-act-pair · gpt-3.5-turbo

    terms related to levels of acceptability or standards in various contexts

    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
    hunter
    -0.68
    ences
    -0.62
    staking
    -0.61
    mares
    -0.60
    dragon
    -0.60
    eries
    -0.59
    stro
    -0.57
    etti
    -0.56
     trek
    -0.56
     Trip
    -0.56
    POSITIVE LOGITS
     acceptable
    3.52
    acceptable
    2.49
     permissible
    1.96
     unacceptable
    1.96
     satisfactory
    1.75
     allowable
    1.75
     toler
    1.70
     tolerated
    1.66
     accepted
    1.48
     manageable
    1.45
    Activations Density 0.017%

    No Known Activations