© 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. 7910
    Prev
    Next
    INDEX
    Explanations

    phrases where someone acknowledges something

    oai_token-act-pair · gpt-3.5-turbo

    instances of acknowledgment and recognition

    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
     known
    -0.70
     continued
    -0.64
     estimated
    -0.63
     supposed
    -0.62
     looming
    -0.60
     required
    -0.60
     added
    -0.60
     protected
    -0.60
     proven
    -0.59
     ranked
    -0.59
    POSITIVE LOGITS
     acknowledge
    1.95
     accuse
    1.87
     concede
    1.86
     criticize
    1.81
     speculate
    1.76
     recognise
    1.70
     contemplate
    1.67
     conclude
    1.67
     indulge
    1.65
     propose
    1.65
    Activations Density 0.076%

    No Known Activations