© 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. 9-RES-JB
    11. 16326
    Prev
    Next
    INDEX
    Explanations

    phrases that express confidence, affirmation, or denial

    oai_token-act-pair · gpt-3.5-turbo

    the presence and frequency of the phrases "I am" and "you are."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ð
    -0.73
    esm
    -0.66
    rarily
    -0.65
    bies
    -0.65
    udeau
    -0.62
     Guys
    -0.61
     Gap
    -0.60
    roll
    -0.59
    angled
    -0.59
    othal
    -0.58
    POSITIVE LOGITS
     hereby
    1.13
     aware
    1.00
     presently
    1.00
     indeed
    0.99
     not
    0.99
     unable
    0.99
    nt
    0.96
     NOT
    0.95
     currently
    0.95
     obliged
    0.89
    Activations Density 0.235%

    No Known Activations