© 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. 8-RES-JB
    11. 19380
    Prev
    Next
    INDEX
    Explanations

    titles or headings within a document

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to "the" indicating a focus on specific subjects or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogie
    -0.77
     TAMADRA
    -0.67
    mares
    -0.65
    ilee
    -0.64
    erto
    -0.64
    Ore
    -0.63
    artment
    -0.63
    ormal
    -0.60
    ican
    -0.60
    Kings
    -0.60
    POSITIVE LOGITS
     standpoint
    1.63
     vantage
    1.47
     outset
    1.44
     perspective
    1.42
     perspectives
    1.22
     viewpoint
    1.20
     angles
    1.07
     angle
    0.97
     inception
    0.97
     onset
    0.97
    Activations Density 0.131%

    No Known Activations