© 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. 11151
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names as pairs or individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of individuals' names or titles in context

    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
    olutions
    -0.84
    eco
    -0.77
    ipt
    -0.68
    itizens
    -0.67
    izen
    -0.65
     Higher
    -0.64
     metab
    -0.64
     adaptations
    -0.64
     outputs
    -0.63
    pec
    -0.61
    POSITIVE LOGITS
     whom
    1.60
     who
    1.27
    who
    1.24
     whose
    1.14
    whose
    1.13
     Jr
    1.11
     Sr
    0.95
    Jr
    0.88
     although
    0.85
     albeit
    0.81
    Activations Density 0.271%

    No Known Activations