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. 4419
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of kidnapping and related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or characters

    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
     Legion
    -0.65
     secular
    -0.63
     fold
    -0.62
     burns
    -0.62
     tre
    -0.62
     semi
    -0.61
     inspir
    -0.61
     reviews
    -0.61
     UL
    -0.61
     prohibited
    -0.61
    POSITIVE LOGITS
    apper
    4.57
    appers
    3.16
    apping
    1.92
    apped
    1.79
    appings
    1.68
    aps
    1.36
    appy
    1.20
    appa
    1.18
    ipper
    1.16
    ap
    1.10
    Activations Density 0.011%

    No Known Activations