Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 17021
    Prev
    Next
    INDEX
    Explanations

    terms related to specific acronyms and proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    acronyms and abbreviations related to organizations and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %.
    -1.16
     ".
    -1.05
     ."
    -1.05
     '.
    -1.02
    !".
    -0.88
     };
    -0.87
    .</
    -0.85
    +.
    -0.84
    `.
    -0.83
    $.
    -0.81
    POSITIVE LOGITS
    )
    1.72
    )'
    1.54
    )—
    1.46
    )"
    1.43
    )/
    1.31
    ?)
    1.29
    )-
    1.28
    ')
    1.28
    /)
    1.25
    )--
    1.25
    Activations Density 0.310%

    No Known Activations