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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 3777
    Prev
    Next
    INDEX
    Explanations

    words related to strong desires or cravings, such as "clamoring" and "lust"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cravings or desires

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

    No Comments

    Negative Logits
    selection
    -0.68
     Agency
    -0.63
    Georgia
    -0.63
    stood
    -0.62
     PBS
    -0.61
    ĻĤ
    -0.61
    IELD
    -0.61
    basketball
    -0.60
    pend
    -0.59
     portfolio
    -0.58
    POSITIVE LOGITS
     clam
    1.13
    borgh
    0.85
    iously
    0.84
    eless
    0.83
    orously
    0.81
    orious
    0.75
    ivery
    0.75
    acy
    0.74
    mong
    0.73
    orous
    0.73
    Activations Density 0.009%

    No Known Activations