© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 9278
    Prev
    Next
    INDEX
    Explanations

    words related to new, unique, or interesting concepts or ideas

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to novelty, gimmicks, and social trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     redes
    -0.72
     Lama
    -0.70
    tein
    -0.66
    fax
    -0.65
    lem
    -0.64
    alted
    -0.63
     Mate
    -0.62
     complicit
    -0.61
    semb
    -0.60
    rigan
    -0.60
    POSITIVE LOGITS
     novelty
    0.90
     gimm
    0.81
    soDeliveryDate
    0.78
    é¾įå¥ij士
    0.76
    icky
    0.69
    iqueness
    0.69
     rele
    0.66
     proble
    0.66
    timer
    0.65
     Flavoring
    0.64
    Activations Density 0.025%

    No Known Activations