© 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 EvalsExportsinterp-engineNEWAPI 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. 11364
    Prev
    Next
    INDEX
    Explanations

    phrases related to interviews or conversations with individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "spoke" or its variations indicating communication

    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
    eers
    -0.67
    ilts
    -0.61
     ILCS
    -0.60
     inhab
    -0.59
    isal
    -0.58
     obe
    -0.57
    ————
    -0.56
    herent
    -0.56
    eer
    -0.56
     misplaced
    -0.55
    POSITIVE LOGITS
     extensively
    0.98
     glow
    0.74
     about
    0.74
     frankly
    0.71
     briefly
    0.69
     anonymously
    0.68
     bout
    0.65
     exclusively
    0.64
    bitcoin
    0.63
     ABOUT
    0.63
    Activations Density 0.074%

    No Known Activations