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. 6-RES-JB
    6. 22947
    Prev
    Next
    INDEX
    Explanations

    the word "great"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "great"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ople
    -0.94
    clips
    -0.86
    ptives
    -0.79
    qqa
    -0.77
    phrine
    -0.72
    etts
    -0.69
    PD
    -0.69
    PT
    -0.69
    chedel
    -0.68
    rette
    -0.68
    POSITIVE LOGITS
    sword
    1.21
     strides
    1.03
    itud
    0.85
    axe
    0.82
     apes
    0.78
    grand
    0.77
    reek
    0.76
     believer
    0.75
     accomplishment
    0.74
     feats
    0.74
    Activations Density 0.040%

    No Known Activations