© 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. 530
    Prev
    Next
    INDEX
    Explanations

    contractions such as "it's" and "isn't"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating something is subjectively perceived or defined

    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
    ĸļ
    -0.64
     [-
    -0.64
     BB
    -0.62
    ume
    -0.61
     Daly
    -0.61
     Clear
    -0.60
     Harlem
    -0.59
     allegedly
    -0.57
     Gil
    -0.56
    -[
    -0.56
    POSITIVE LOGITS
    rosso
    1.03
     wiser
    0.90
     someday
    0.86
     somew
    0.85
    cheat
    0.80
     misunder
    0.72
    legged
    0.72
     underest
    0.70
     typo
    0.70
    vana
    0.69
    Activations Density 0.341%

    No Known Activations