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. 21271
    Prev
    Next
    INDEX
    Explanations

    sentences indicating a strong sentiment, often emphasizing negativity

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that end with a period

    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
     predec
    -0.62
     expectancy
    -0.61
     contested
    -0.60
     advis
    -0.59
     occupancy
    -0.57
     contingency
    -0.56
     employment
    -0.56
     freight
    -0.56
     submerged
    -0.55
     cradle
    -0.55
    POSITIVE LOGITS
    tumblr
    1.30
    jpg
    1.24
    txt
    1.16
    gif
    1.14
    wav
    1.14
    blogspot
    1.14
    exe
    1.13
    png
    1.13
     :)
    1.11
     ;)
    1.09
    Activations Density 0.314%

    No Known Activations