© 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. 17144
    Prev
    Next
    INDEX
    Explanations

    phrases related to possessing or carrying something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bear" in various contexts

    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
    apo
    -0.80
    inx
    -0.76
    esters
    -0.73
    opus
    -0.73
    iltration
    -0.73
    lectic
    -0.71
    enta
    -0.68
    ###
    -0.67
    earch
    -0.67
    urated
    -0.67
    POSITIVE LOGITS
    bear
    0.88
     fruit
    0.86
    beit
    0.85
     witness
    0.84
     Bears
    0.81
    weight
    0.76
     borne
    0.75
    Charges
    0.74
     bear
    0.73
    ably
    0.73
    Activations Density 0.019%

    No Known Activations