© 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. 0-RES-JB
    11. 2817
    Prev
    Next
    INDEX
    Explanations

    odd or unusual occurrences or situations

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "odd" 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
    lain
    -0.81
    ader
    -0.71
    venge
    -0.70
     Fully
    -0.65
    ride
    -0.64
    ETS
    -0.64
    Rated
    -0.64
    buster
    -0.63
    blast
    -0.62
    ade
    -0.61
    POSITIVE LOGITS
     odd
    3.52
     strange
    1.90
     weird
    1.79
     unusual
    1.68
     inexplicable
    1.55
     bizarre
    1.54
     oddly
    1.53
    odd
    1.51
     occasional
    1.49
     peculiar
    1.44
    Activations Density 0.018%

    No Known Activations