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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 2673
    Prev
    Next
    INDEX
    Explanations

    instances where something is identified, highlighted, or made prominent

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "marked" used to indicate significance or highlight particular events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    APS
    -0.75
    urus
    -0.75
    rouch
    -0.73
    ADS
    -0.73
    CHA
    -0.71
    ettel
    -0.71
    halla
    -0.69
    ilk
    -0.68
    isance
    -0.68
    adra
    -0.68
    POSITIVE LOGITS
     marked
    1.06
     marks
    0.91
    ocument
    0.89
    paren
    0.83
     marking
    0.82
    marked
    0.80
     signs
    0.79
     warr
    0.75
     markings
    0.73
    paralle
    0.73
    Activations Density 0.008%

    No Known Activations