© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 206
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs indicating statements or actions

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of a specific pronoun, indicating focus on a particular individual

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    noon
    -0.84
    uits
    -0.69
    rocket
    -0.68
    NAT
    -0.66
    iries
    -0.65
     differential
    -0.61
     intervening
    -0.60
     Impact
    -0.60
    atible
    -0.59
     Bundes
    -0.58
    POSITIVE LOGITS
     said
    1.02
     joked
    0.99
     laughed
    0.98
     wrote
    0.97
     exclaimed
    0.90
     replied
    0.90
     tweeted
    0.90
     says
    0.89
     remarked
    0.89
    'd
    0.88
    Activations Density 0.056%

    No Known Activations