© 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. 9-RES-JB
    11. 15832
    Prev
    Next
    INDEX
    Explanations

    promotional content related to newsletters and website features

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to engaging with an audience or promoting content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hee
    -0.66
    ident
    -0.61
    urized
    -0.61
    oft
    -0.60
    NAT
    -0.59
    face
    -0.58
     inverted
    -0.57
    quote
    -0.57
     hardened
    -0.56
     largeDownload
    -0.55
    POSITIVE LOGITS
    pload
    0.81
    ]+
    0.67
    »Ĵ
    0.65
     Flavoring
    0.64
    %]
    0.64
    ]);
    0.64
    rawdownloadcloneembedreportprint
    0.63
    ixture
    0.61
    farious
    0.61
     unlocks
    0.60
    Activations Density 0.042%

    No Known Activations