© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 2792
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the surname "Oli"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix 'oli'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rants
    -0.83
    */(
    -0.80
    dash
    -0.79
    rique
    -0.79
    eer
    -0.78
    spin
    -0.78
    liest
    -0.77
    lied
    -0.76
    lain
    -0.75
    ienced
    -0.72
    POSITIVE LOGITS
    ague
    1.04
    oli
    1.03
    zzo
    1.03
    ère
    1.01
    ennes
    0.91
    aceae
    0.88
    Äĩ
    0.86
    oti
    0.85
    ptin
    0.84
    zzi
    0.82
    Activations Density 0.006%

    No Known Activations