© 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. 14530
    Prev
    Next
    INDEX
    Explanations

    proper names and surnames

    oai_token-act-pair · gpt-3.5-turbo

    names of people, particularly those related to political or public figures

    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
    xual
    -0.88
    theless
    -0.82
    vous
    -0.81
    schild
    -0.70
     versa
    -0.69
     endif
    -0.68
    vironment
    -0.68
     tame
    -0.68
    WAYS
    -0.67
     coli
    -0.67
    POSITIVE LOGITS
    olin
    1.10
    ahar
    0.92
     Torn
    0.92
    iat
    0.92
    iana
    0.90
    oor
    0.90
    iant
    0.87
    adium
    0.87
    emonium
    0.86
    arus
    0.84
    Activations Density 0.021%

    No Known Activations