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

    Neuronpedia

    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. 6-RES-JB
    11. 12870
    Prev
    Next
    INDEX
    Explanations

    mentions of academic studies or research

    oai_token-act-pair · gpt-3.5-turbo

    references to academic studies or research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rising
    -0.66
     fitt
    -0.64
    udeau
    -0.63
     chopping
    -0.61
     ILCS
    -0.60
    antha
    -0.60
     bonded
    -0.60
     mustard
    -0.59
     sequest
    -0.58
     abducted
    -0.58
    POSITIVE LOGITS
    udo
    0.87
    study
    0.85
    Study
    0.82
     conducted
    0.81
    iveness
    0.75
     methodology
    0.74
    ãĥĻ
    0.72
     Participant
    0.71
    UF
    0.69
     abroad
    0.69
    Activations Density 0.032%

    No Known Activations