© 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. 7-RES-JB
    11. 17998
    Prev
    Next
    INDEX
    Explanations

    words related to specific geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific articles and conjunctions, particularly "a", as well as elements related to natural resources and wildlife

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.72
     Lambert
    -0.59
     Grace
    -0.57
    mort
    -0.55
    baugh
    -0.54
    Kay
    -0.53
     Ki
    -0.53
    Jackson
    -0.53
     Chambers
    -0.52
    è»
    -0.52
    POSITIVE LOGITS
    anwhile
    0.75
    ateral
    0.70
    tarians
    0.62
    ennett
    0.60
     tradem
    0.59
     destro
    0.57
    hetto
    0.57
    EStream
    0.56
    ãĥĨ
    0.55
    acs
    0.55
    Activations Density 0.199%

    No Known Activations