© 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. 6035
    Prev
    Next
    INDEX
    Explanations

    terms related to lists or items to be checked off

    oai_token-act-pair · gpt-3.5-turbo

    items related to various types of objects or categories

    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
     Instr
    -0.60
    lude
    -0.59
    bart
    -0.59
    tein
    -0.58
    aband
    -0.57
    ropolis
    -0.57
    lein
    -0.55
    ministic
    -0.54
    odox
    -0.53
    eworld
    -0.52
    POSITIVE LOGITS
     alike
    1.99
     respectively
    1.86
    depending
    0.83
     combined
    0.83
     simultaneously
    0.80
    .
    0.80
     sectors
    0.79
     interchange
    0.72
     depending
    0.69
     combo
    0.67
    Activations Density 0.588%

    No Known Activations