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. 0-RES-JB
    6. 22107
    Prev
    Next
    INDEX
    Explanations

    terms related to strength or power

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to potency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Matthews
    -0.82
    rack
    -0.79
     Offline
    -0.77
    ulia
    -0.74
    antage
    -0.71
    igne
    -0.71
     Sle
    -0.70
     Dropbox
    -0.70
     ripe
    -0.69
     Luxembourg
    -0.66
    POSITIVE LOGITS
     potent
    2.34
     potency
    1.48
     brace
    1.41
     ginger
    1.16
     agon
    1.14
    mable
    1.07
    otent
    0.96
     depleted
    0.96
     phosph
    0.95
     psycho
    0.94
    Activations Density 0.035%

    No Known Activations