Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 20947
    Prev
    Next
    INDEX
    Explanations

    words related to internal organs, specifically the brain and heart

    oai_token-act-pair · gpt-3.5-turbo

    references to the brain and emotional connections, particularly involving hearts and minds

    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
    ression
    -0.70
    ressive
    -0.67
    ALLY
    -0.67
    Recomm
    -0.66
    Delivery
    -0.66
    BUG
    -0.63
    rip
    -0.62
    onomy
    -0.59
     Apocalypse
    -0.58
    Definition
    -0.56
    POSITIVE LOGITS
    paces
    1.51
    chool
    1.44
    mith
    1.43
    pace
    1.42
    pring
    1.42
    creen
    1.40
    hips
    1.31
    hare
    1.23
    peed
    1.23
    cale
    1.23
    Activations Density 0.184%

    No Known Activations