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. 19542
    Prev
    Next
    INDEX
    Explanations

    phrases related to suitability or appropriateness

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe the suitability of something for a specific purpose or audience

    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
    aura
    -0.78
    dash
    -0.77
     VIDEOS
    -0.72
    ds
    -0.68
    ults
    -0.67
    uli
    -0.66
     helicop
    -0.65
    ulhu
    -0.65
    semble
    -0.64
    iq
    -0.64
    POSITIVE LOGITS
     suited
    0.91
     fit
    0.83
     suitable
    0.75
     fitt
    0.74
    folios
    0.72
     candidates
    0.71
     fitting
    0.71
    intendent
    0.70
     fits
    0.70
     climates
    0.69
    Activations Density 0.041%

    No Known Activations