Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 14643
    Prev
    Next
    INDEX
    Explanations

    information or news about specific events or conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate strong recommendations or must-watch content

    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
     organisation
    -0.39
     Belfast
    -0.39
     organised
    -0.38
     programme
    -0.38
     Shutterstock
    -0.36
     licences
    -0.36
     organisations
    -0.35
     Perspective
    -0.34
     favourites
    -0.33
     organis
    -0.33
    POSITIVE LOGITS
    omever
    0.41
    otom
    0.36
     aven
    0.34
    eday
    0.34
    .")
    0.34
    """
    0.34
    ageddon
    0.32
    ĨĴ
    0.32
     Kappa
    0.32
    PDATE
    0.31
    Activations Density 3.767%

    No Known Activations