© 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. 12642
    Prev
    Next
    INDEX
    Explanations

    comma punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    lists of values or comparisons involving numerical data

    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
    geon
    -0.68
     Balanced
    -0.65
    è£ħ
    -0.62
     unlocked
    -0.61
    hest
    -0.59
    kj
    -0.58
     Charg
    -0.57
    llan
    -0.56
     Nex
    -0.56
    cca
    -0.56
    POSITIVE LOGITS
     uh
    1.07
     um
    0.99
     albeit
    0.87
     ah
    0.80
     oh
    0.72
    =-=-
    0.71
    say
    0.70
     gasp
    0.70
    wait
    0.69
     say
    0.65
    Activations Density 0.136%

    No Known Activations