© 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 EvalsExportsAPI 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. 10-RES-JB
    11. 21602
    Prev
    Next
    INDEX
    Explanations

    polls conducted by different organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to opinion polls and survey results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leilan
    -0.82
     spac
    -0.70
     Flavoring
    -0.67
     Horus
    -0.64
    complex
    -0.64
    ivable
    -0.61
     Centauri
    -0.60
    ipedia
    -0.60
     Invention
    -0.59
     Nib
    -0.59
    POSITIVE LOGITS
     conducted
    1.18
    ster
    1.16
    sters
    1.12
     polled
    1.07
     respondent
    1.07
     respondents
    1.07
     polling
    0.97
    STER
    0.96
     commissioned
    0.92
     surveyed
    0.90
    Activations Density 0.059%

    No Known Activations