© 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. 1594
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to entities and organizations

    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
    ICAN
    -0.81
    FML
    -0.73
    hani
    -0.73
     pione
    -0.72
    PDATE
    -0.72
    ufact
    -0.71
    ailability
    -0.70
    inki
    -0.69
    schild
    -0.68
     subur
    -0.68
    POSITIVE LOGITS
    rete
    0.66
    imates
    0.62
    bourg
    0.61
     Luthor
    0.59
     Nex
    0.59
    phia
    0.58
    ν
    0.56
    isner
    0.56
     Neph
    0.55
    modules
    0.55
    Activations Density 0.403%

    No Known Activations