© 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. 20786
    Prev
    Next
    INDEX
    Explanations

    characters or symbols associated with emoticons or special characters

    oai_token-act-pair · gpt-3.5-turbo

    various symbols and special characters

    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
     independ
    -0.67
     Accord
    -0.66
     Militia
    -0.64
     suicide
    -0.64
     applic
    -0.63
     suspensions
    -0.61
     delegates
    -0.61
     simultane
    -0.61
     Virgin
    -0.60
     Creation
    -0.60
    POSITIVE LOGITS
    ł
    2.09
    ©
    2.07
    Ģ
    2.05
    Ĩ
    2.04
    ¸
    2.03
    ¹
    2.03
    ĥ
    2.03
    Ķ
    2.02
    ī
    2.02
    Ĭ
    2.02
    Activations Density 0.031%

    No Known Activations