© 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. 0-RES-JB
    11. 6825
    Prev
    Next
    INDEX
    Explanations

    instances of the word "talked"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "talked."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤº
    -0.63
     apex
    -0.62
     registration
    -0.61
    atures
    -0.61
     deposit
    -0.60
     Reg
    -0.59
     blaze
    -0.57
     mark
    -0.56
    ature
    -0.56
     due
    -0.56
    POSITIVE LOGITS
     talked
    3.23
     discussed
    2.09
     spoke
    1.90
    talk
    1.79
     talk
    1.74
     listened
    1.59
     preached
    1.56
     alluded
    1.54
     debated
    1.53
     talks
    1.50
    Activations Density 0.010%

    No Known Activations