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. 1-RES-JB
    6. 1332
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to being filled or infested with something negative or problematic

    oai_token-act-pair · gpt-3.5-turbo

    terms related to issues, problems, or negative conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ift
    -0.78
    mpeg
    -0.72
     sidx
    -0.70
    pressed
    -0.66
    ifted
    -0.65
    uber
    -0.65
    hal
    -0.63
    cel
    -0.61
    friend
    -0.61
    cell
    -0.59
    POSITIVE LOGITS
     plagued
    0.94
     littered
    0.82
     rife
    0.81
     riddled
    0.74
    DOS
    0.71
     Mania
    0.69
    entimes
    0.68
    riad
    0.67
    rodu
    0.67
    slaught
    0.65
    Activations Density 0.022%

    No Known Activations