© 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. 2041
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "ero"

    oai_token-act-pair · gpt-3.5-turbo

    words that represent different forms or variations of the word "hero."

    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
    ividual
    -0.98
    abase
    -0.85
    ually
    -0.72
    hips
    -0.70
    ĸļ
    -0.69
    ivities
    -0.68
    eenth
    -0.67
    tin
    -0.67
    grave
    -0.66
    ership
    -0.65
    POSITIVE LOGITS
    cephal
    0.93
    zzi
    0.88
    vous
    0.84
    quin
    0.83
    ffe
    0.83
    ffic
    0.81
    zza
    0.79
    edia
    0.78
    zo
    0.75
    ctor
    0.75
    Activations Density 0.043%

    No Known Activations