© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 17798
    Prev
    Next
    INDEX
    Explanations

    entities or terms related to tutorials and educational content

    oai_token-act-pair · gpt-3.5-turbo

    mentions of educational institutions and tutorship

    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
    ohyd
    -0.68
    ppo
    -0.66
     Flavoring
    -0.66
    ensitive
    -0.65
     Chandler
    -0.62
    ONES
    -0.62
     Lobby
    -0.62
     Gy
    -0.61
     Lima
    -0.61
     hemp
    -0.60
    POSITIVE LOGITS
    sonian
    0.93
    angelo
    0.86
    endi
    0.82
    heet
    0.79
    imum
    0.76
    ments
    0.76
    TING
    0.75
    yang
    0.72
    utils
    0.71
    nance
    0.71
    Activations Density 0.066%

    No Known Activations