© 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. 4-RES-JB
    11. 10370
    Prev
    Next
    INDEX
    Explanations

    mentions of specific events or people's names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "atra" and related references, likely within a political or social context

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

    No Comments

    Negative Logits
     GF
    -0.70
    igating
    -0.69
    Trend
    -0.68
    PG
    -0.67
    rats
    -0.67
    picking
    -0.67
    ective
    -0.67
     Stam
    -0.66
     suspic
    -0.66
    onet
    -0.65
    POSITIVE LOGITS
    é¾įåĸļ士
    0.85
    issance
    0.83
    agne
    0.80
    zzo
    0.80
     Mae
    0.77
    phrine
    0.76
    sonian
    0.75
    bows
    0.75
    enei
    0.74
     Jinn
    0.72
    Activations Density 0.020%

    No Known Activations