© 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. 3-RES-JB
    11. 16360
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to specific people, particularly males

    oai_token-act-pair · gpt-3.5-turbo

    references to male characters and their actions or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Springs
    -0.75
    idge
    -0.72
    ourcing
    -0.69
    DAQ
    -0.69
     Bundes
    -0.68
     Tradable
    -0.66
     EW
    -0.66
    nb
    -0.66
    isites
    -0.66
    é¾
    -0.65
    POSITIVE LOGITS
    panic
    0.81
    ather
    0.77
     antagonist
    0.76
     antagonists
    0.75
     assailant
    0.73
    ctor
    0.72
     semen
    0.71
     ejac
    0.70
     abusive
    0.70
     penis
    0.70
    Activations Density 0.285%

    No Known Activations