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. 9527
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences with a definitive or authoritative tone

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks or sentence endings

    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
     souven
    -0.74
     brill
    -0.74
    morrow
    -0.73
    minster
    -0.72
     bye
    -0.70
    rament
    -0.68
     booth
    -0.67
     congr
    -0.67
     coord
    -0.66
     pard
    -0.66
    POSITIVE LOGITS
     Specifically
    1.65
    Specifically
    1.46
     Among
    1.25
     Notably
    1.24
     Whereas
    1.21
     Essentially
    1.21
    emphasis
    1.21
     Included
    1.16
     Particularly
    1.14
     According
    1.13
    Activations Density 0.540%

    No Known Activations