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. 3-RES-JB
    6. 19723
    Prev
    Next
    INDEX
    Explanations

    words related to high activity or involvement in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to being "active."

    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
    aneers
    -0.80
    AMI
    -0.77
    ageddon
    -0.75
    umbo
    -0.75
    unts
    -0.74
    yth
    -0.74
    OUGH
    -0.72
    ĸļ
    -0.69
    obyl
    -0.68
    ERO
    -0.67
    POSITIVE LOGITS
     active
    0.92
     participation
    0.89
     newsp
    0.83
     duty
    0.83
     ingredient
    0.82
     Directory
    0.78
    ives
    0.78
     involvement
    0.77
     participant
    0.76
     activity
    0.75
    Activations Density 0.010%

    No Known Activations