© 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. 6-RES-JB
    11. 10993
    Prev
    Next
    INDEX
    Explanations

    numerical codes or references

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and model names related to audio equipment or devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    panic
    -0.81
    TPPStreamerBot
    -0.76
    opian
    -0.73
    blogs
    -0.70
    otal
    -0.67
    onal
    -0.67
    tones
    -0.67
    abytes
    -0.64
    ipedia
    -0.64
    etimes
    -0.63
    POSITIVE LOGITS
    £ı
    0.94
    cv
    0.82
    PLA
    0.81
    III
    0.75
    CV
    0.72
    301
    0.72
    651
    0.72
    753
    0.72
    307
    0.71
    DH
    0.71
    Activations Density 0.167%

    No Known Activations