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. 18069
    Prev
    Next
    INDEX
    Explanations

    phrases related to hiding or concealing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Hide" or variations, indicating a focus on concealment or obfuscation in the text

    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
    etheless
    -0.90
    odic
    -0.85
    ammy
    -0.78
    ionic
    -0.77
    ilingual
    -0.77
    eele
    -0.76
    ulz
    -0.74
    iod
    -0.72
    theless
    -0.72
    bably
    -0.71
    POSITIVE LOGITS
     Caption
    1.04
     Hide
    0.99
    Hide
    0.97
    away
    0.97
    ously
    0.72
    Emb
    0.69
    ãĥĥãĥī
    0.69
    Pic
    0.69
    hide
    0.68
    Track
    0.68
    Activations Density 0.011%

    No Known Activations