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. 18310
    Prev
    Next
    INDEX
    Explanations

    phrases related to invasion or infringement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "invade" or its variations

    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
    geon
    -0.63
     horizontally
    -0.61
     untreated
    -0.59
    ©¶æ
    -0.59
     hol
    -0.59
     Shepard
    -0.59
    MAT
    -0.59
     Tale
    -0.58
     preferred
    -0.58
     bare
    -0.57
    POSITIVE LOGITS
    asions
    1.46
    incible
    1.44
    ulnerable
    1.44
    igor
    1.44
    oked
    1.42
    asion
    1.36
    ulnerability
    1.36
    itational
    1.36
    olve
    1.35
    itations
    1.33
    Activations Density 0.028%

    No Known Activations