© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 19941
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer programming and technology, particularly mentioning the word 'Console'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific programming interfaces or commands

    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
    jon
    -0.75
    uf
    -0.74
    jah
    -0.72
    boa
    -0.70
    manuel
    -0.66
     Zar
    -0.65
     Zurich
    -0.63
     Zak
    -0.63
     Vald
    -0.63
    adiq
    -0.63
    POSITIVE LOGITS
     Console
    3.01
    Console
    1.84
     Bronze
    0.92
     Pastebin
    0.83
    WARE
    0.82
     Desktop
    0.80
     Extras
    0.78
    wcs
    0.77
     Output
    0.72
    Output
    0.71
    Activations Density 0.009%

    No Known Activations