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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11992
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "periodic."

    oai_token-act-pair · gpt-3.5-turbo

    references to periodic processes or patterns

    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
     Archdemon
    -0.72
    FTWARE
    -0.70
    CONCLUS
    -0.68
     Alexandria
    -0.67
    VILLE
    -0.66
    RESULTS
    -0.64
     srfAttach
    -0.60
     fold
    -0.60
     burner
    -0.60
     Von
    -0.59
    POSITIVE LOGITS
     periodic
    1.37
    ozo
    0.84
    ept
    0.80
    y
    0.80
    opian
    0.80
    imar
    0.78
    apons
    0.78
    yre
    0.76
    yy
    0.75
    hn
    0.73
    Activations Density 0.001%

    No Known Activations