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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22493
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was" and similar forms, indicating actions or occurrences in the context of events or situations

    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
    holder
    -0.68
    erential
    -0.67
     slots
    -0.64
    holders
    -0.63
     expires
    -0.62
     newsletters
    -0.61
    keeping
    -0.61
    wealth
    -0.61
     Cosponsors
    -0.60
     Preferences
    -0.60
    POSITIVE LOGITS
     perpetrated
    1.28
     attributed
    1.08
     blamed
    1.07
     preceded
    1.06
     prosecuted
    1.05
     investigated
    1.04
     filmed
    1.03
     aven
    1.02
     prevented
    1.01
     witnessed
    1.01
    Activations Density 0.204%

    No Known Activations