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. 8-RES-JB
    6. 17946
    Prev
    Next
    INDEX
    Explanations

    phrases related to serious allegations

    oai_token-act-pair · gpt-3.5-turbo

    references to allegations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    keys
    -0.89
    tz
    -0.76
    arton
    -0.73
    å¸
    -0.72
     busiest
    -0.71
    oppy
    -0.71
    patch
    -0.71
    skill
    -0.71
    tem
    -0.69
    perm
    -0.68
    POSITIVE LOGITS
     allegations
    1.13
     alleging
    1.11
     leveled
    1.07
     accusing
    1.07
     levied
    1.04
     against
    1.03
     accusation
    1.02
     accusations
    1.02
     allegation
    1.02
     alleges
    1.00
    Activations Density 0.061%

    No Known Activations