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. 11-RES-JB
    6. 8668
    Prev
    Next
    INDEX
    Explanations

    actions or events related to causing someone to take off their clothes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verbs "make" and "made" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hips
    -0.78
     Niet
    -0.69
    Fram
    -0.67
    2019
    -0.67
    bour
    -0.66
    oir
    -0.66
     privilege
    -0.65
    hip
    -0.64
    ror
    -0.63
    Mania
    -0.62
    POSITIVE LOGITS
     arrangements
    1.15
     haste
    1.08
     landfall
    1.02
     preparations
    1.01
     sure
    0.98
     excuses
    0.98
     merry
    0.96
     arrang
    0.95
     noises
    0.93
     repairs
    0.93
    Activations Density 0.105%

    No Known Activations