© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 6048
    Prev
    Next
    INDEX
    Explanations

    terms related to data and information processing, particularly focusing on subject matter and content

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to subject matter and structural elements in various contexts

    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
    DAY
    -0.85
    STAR
    -0.83
    Case
    -0.76
    Birth
    -0.76
    ighthouse
    -0.74
    prison
    -0.73
    Rail
    -0.73
    sonian
    -0.72
    Mos
    -0.72
    ofi
    -0.72
    POSITIVE LOGITS
     optimization
    0.84
     continuum
    0.78
     specialization
    0.75
     flexibility
    0.75
     associated
    0.74
     fragmentation
    0.71
     deduction
    0.71
     enhancements
    0.70
     modification
    0.70
     changes
    0.70
    Activations Density 0.642%

    No Known Activations