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. 15999
    Prev
    Next
    INDEX
    Explanations

    words related to generations or processes involving multiple generations

    oai_token-act-pair · gpt-3.5-turbo

    words related to "ational" or "ationally" concepts, indicating a focus on various attributes of states or conditions

    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
     mistress
    -0.73
     Gi
    -0.59
     streaks
    -0.58
     charged
    -0.58
     vict
    -0.57
     Flo
    -0.57
     sweat
    -0.57
     winds
    -0.55
    beard
    -0.55
     Bundle
    -0.55
    POSITIVE LOGITS
    ational
    4.65
    ationally
    2.24
    ations
    1.88
    ATIONAL
    1.78
    ative
    1.60
    ATION
    1.48
    ation
    1.47
    ATIONS
    1.40
    atory
    1.36
    acion
    1.31
    Activations Density 0.016%

    No Known Activations