© 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. 11645
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication or conversation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Talk."

    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
     fig
    -0.72
     imperial
    -0.70
     domin
    -0.68
     ancestral
    -0.68
     mat
    -0.66
     lat
    -0.64
     correctional
    -0.63
     sustain
    -0.63
     executed
    -0.62
     cu
    -0.62
    POSITIVE LOGITS
     Talk
    3.63
    Talk
    3.60
    talk
    3.03
     talk
    2.02
     Talks
    1.92
     Speak
    1.70
     Talking
    1.70
    Talking
    1.64
    talking
    1.62
    speak
    1.39
    Activations Density 0.018%

    No Known Activations