© 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. 7-RES-JB
    11. 23736
    Prev
    Next
    INDEX
    Explanations

    conditional statements starting with "Had"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Had" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outp
    -0.65
    FTWARE
    -0.64
     scrimmage
    -0.62
     sniper
    -0.59
    Rated
    -0.58
     repay
    -0.58
    âĻ¦
    -0.57
     embr
    -0.57
     juggling
    -0.57
     salute
    -0.56
    POSITIVE LOGITS
    iths
    1.06
    rons
    0.92
    ith
    0.91
    hers
    0.90
    luck
    0.87
    nesday
    0.84
     been
    0.82
    rontal
    0.82
    dit
    0.82
    alus
    0.80
    Activations Density 0.067%

    No Known Activations