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. 9-RES-JB
    6. 15172
    Prev
    Next
    INDEX
    Explanations

    similes comparing different situations

    oai_token-act-pair · gpt-3.5-turbo

    comparisons or similes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erity
    -0.92
    iencies
    -0.89
    idates
    -0.82
    iets
    -0.77
    icators
    -0.77
    icator
    -0.73
    icity
    -0.72
    icals
    -0.69
    ixel
    -0.69
    odes
    -0.68
    POSITIVE LOGITS
    lier
    1.34
    liest
    1.25
    lihood
    1.01
     comparing
    0.81
     wildfire
    0.79
     waking
    0.78
     watching
    0.75
    liness
    0.75
     spitting
    0.74
     unto
    0.72
    Activations Density 0.070%

    No Known Activations