© 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. 8-RES-JB
    11. 10040
    Prev
    Next
    INDEX
    Explanations

    the concept of "first" in a sequence or list

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "first."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jong
    -0.88
    anism
    -0.70
    Ïī
    -0.70
    amia
    -0.69
    md
    -0.69
    dain
    -0.68
    each
    -0.67
    PK
    -0.67
    par
    -0.66
    acus
    -0.66
    POSITIVE LOGITS
     thing
    1.33
     question
    1.08
     caveat
    1.04
     reason
    1.02
     lesson
    0.97
     step
    0.93
     clue
    0.91
     casualty
    0.91
     drawback
    0.89
     aspect
    0.89
    Activations Density 0.112%

    No Known Activations