© 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. 3-RES-JB
    11. 1860
    Prev
    Next
    INDEX
    Explanations

    references to news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    commands or prompts to access more information or continue reading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xon
    -0.80
    opard
    -0.72
    WC
    -0.70
    ascal
    -0.67
    UTION
    -0.67
    WP
    -0.67
    VC
    -0.66
    اÙĦ
    -0.65
    FL
    -0.65
    amel
    -0.65
    POSITIVE LOGITS
     aloud
    1.02
     Read
    0.90
    ahead
    0.86
    Write
    0.86
    htaking
    0.84
    estone
    0.81
    iness
    0.80
    sburg
    0.79
    ying
    0.78
    ied
    0.76
    Activations Density 0.018%

    No Known Activations