© 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. 11591
    Prev
    Next
    INDEX
    Explanations

    the word "too" occurring in various sentences

    oai_token-act-pair · gpt-3.5-turbo

    the word "too" and its variations expressing excess or addition

    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
    estamp
    -0.61
    inarily
    -0.60
     plurality
    -0.58
     Hearts
    -0.54
     Berks
    -0.53
    oleon
    -0.53
    osterone
    -0.52
     Eth
    -0.52
    icipated
    -0.52
    atform
    -0.52
    POSITIVE LOGITS
    !:
    0.88
     much
    0.83
    !.
    0.79
    !
    0.77
    !,
    0.76
     tempting
    0.76
     many
    0.74
    .,
    0.74
     :)
    0.74
    ooo
    0.73
    Activations Density 0.033%

    No Known Activations