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. 17952
    Prev
    Next
    INDEX
    Explanations

    specific years mentioned in a scientific context

    oai_token-act-pair · gpt-3.5-turbo

    references to publication years and citations in research

    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
    aepernick
    -0.66
     imagination
    -0.62
    glers
    -0.61
     flooded
    -0.61
     magically
    -0.60
     drowned
    -0.59
     overcrowd
    -0.58
     warranties
    -0.57
    atives
    -0.57
     ancest
    -0.57
    POSITIVE LOGITS
    b
    1.12
    a
    1.08
    ).
    0.92
    ;
    0.83
    )—
    0.83
    )].
    0.83
     ).
    0.82
    ),
    0.81
     unpublished
    0.80
    bda
    0.79
    Activations Density 0.045%

    No Known Activations