© 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. 4048
    Prev
    Next
    INDEX
    Explanations

    words related to speaking and communication

    oai_token-act-pair · gpt-3.5-turbo

    the presence of variations of the word "speak."

    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
     battleground
    -0.64
     withdrawal
    -0.62
     offence
    -0.62
     allergy
    -0.60
     delinquent
    -0.60
     Corps
    -0.60
     Pull
    -0.60
     inactive
    -0.59
     Reduction
    -0.58
     cortisol
    -0.58
    POSITIVE LOGITS
    spe
    4.74
    Spe
    1.79
     Spe
    1.69
    speak
    1.38
    sp
    1.37
    speaking
    1.28
     speakers
    1.17
    spec
    1.17
    speed
    1.14
     speaker
    1.06
    Activations Density 0.010%

    No Known Activations