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. 977
    Prev
    Next
    INDEX
    Explanations

    terms related to investigations, trials, and incidents

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to criminal events and incidents

    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
     spons
    -0.69
    âĹ¼
    -0.66
    Native
    -0.64
     ILCS
    -0.64
    hemy
    -0.62
    soever
    -0.61
    SAY
    -0.61
     Sins
    -0.61
    zac
    -0.59
    avis
    -0.59
    POSITIVE LOGITS
     lasted
    1.39
     occurred
    1.21
     began
    1.20
     ended
    1.18
     happened
    1.13
     progressed
    1.12
     culmin
    1.09
     started
    1.09
     unfolded
    1.09
     proceeded
    1.08
    Activations Density 0.307%

    No Known Activations