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. 10-RES-JB
    6. 19410
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical issues or errors

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating error messages or issues with subscriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fortun
    -0.62
     rave
    -0.59
     favorably
    -0.57
     frontline
    -0.55
     helicop
    -0.54
     unpre
    -0.53
     ut
    -0.53
     princ
    -0.53
    ³³³³³³³³³³³³³³³³
    -0.52
     coord
    -0.52
    POSITIVE LOGITS
     Invalid
    1.35
    thia
    0.75
    ose
    0.71
    ally
    0.70
    OSE
    0.69
    rome
    0.65
    oses
    0.64
     Nicotine
    0.63
    Invalid
    0.60
    atta
    0.60
    Activations Density 0.012%

    No Known Activations