© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4982
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names beginning with 'Had'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Had" indicating past actions or events

    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
     automatically
    -0.62
    Ħ¢
    -0.61
     instant
    -0.59
    ogle
    -0.59
    pires
    -0.59
     vary
    -0.58
    eker
    -0.57
     trolling
    -0.56
     involves
    -0.56
     involve
    -0.55
    POSITIVE LOGITS
     Had
    3.71
    Had
    2.79
    had
    1.65
     Were
    1.52
     Was
    1.46
     Has
    1.40
     Did
    1.32
    Were
    1.24
     Went
    1.20
    Was
    1.19
    Activations Density 0.010%

    No Known Activations