© 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. 11-RES-JB
    11. 3725
    Prev
    Next
    INDEX
    Explanations

    mentions of initial experiences or beginnings

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal experiences and first encounters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unfocusedRange
    -0.67
    requires
    -0.64
     varies
    -0.63
    ALSE
    -0.61
     vary
    -0.60
     abound
    -0.59
    VERSION
    -0.58
    uzzle
    -0.57
     concentration
    -0.57
     deficit
    -0.57
    POSITIVE LOGITS
     heard
    1.11
     learned
    1.07
     realized
    1.07
     realised
    1.07
     saw
    1.06
     woke
    1.01
     learnt
    1.01
     clicked
    1.00
     discovered
    1.00
     stumbled
    0.99
    Activations Density 0.179%

    No Known Activations