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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21022
    Prev
    Next
    INDEX
    Explanations

    measurements or specific physical characteristics

    oai_token-act-pair · gpt-3.5-turbo

    measurements and descriptors related to size and condition

    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
    biased
    -0.92
    reasonable
    -0.87
    OIL
    -0.82
    ecause
    -0.82
    serious
    -0.80
    Ô
    -0.80
    osponsors
    -0.76
    Specific
    -0.76
    ascript
    -0.76
    different
    -0.75
    POSITIVE LOGITS
     confines
    1.16
     facility
    0.96
    ness
    0.92
     structure
    0.91
     outpost
    0.90
     structures
    0.85
     spectacle
    0.85
     blaze
    0.84
     affair
    0.84
     creatures
    0.83
    Activations Density 0.215%

    No Known Activations