© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 972
    Prev
    Next
    INDEX
    Explanations

    situations or events that have a sense of completion or finality

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metic
    -0.77
     corrid
    -0.75
     tyr
    -0.72
     quir
    -0.72
    uly
    -0.71
    oshenko
    -0.70
     purse
    -0.69
     challeng
    -0.67
     suspic
    -0.66
     gobl
    -0.66
    POSITIVE LOGITS
     However
    0.96
     Needless
    0.95
     Additionally
    0.92
     Nevertheless
    0.91
     Nonetheless
    0.89
     Whereas
    0.89
     Fortunately
    0.88
     Luckily
    0.88
     Therefore
    0.88
     Furthermore
    0.88
    Activations Density 1.608%

    No Known Activations