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. 19435
    Prev
    Next
    INDEX
    Explanations

    statements expressing support or validation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to support or validation

    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
    nel
    -0.75
    anny
    -0.73
    ities
    -0.70
     newsp
    -0.69
    pox
    -0.68
    inational
    -0.65
     Hebdo
    -0.65
     irony
    -0.64
    entric
    -0.63
     ILCS
    -0.63
    POSITIVE LOGITS
    raise
    0.75
    hard
    0.75
    track
    0.73
    byn
    0.73
    abies
    0.71
    drive
    0.69
    ament
    0.67
    taking
    0.66
    GROUND
    0.65
    lash
    0.65
    Activations Density 0.038%

    No Known Activations