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. 7924
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a change or development in a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate conditions or circumstances surrounding actions or situations

    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
     âĨij
    -0.83
    Recommend
    -0.83
     ®
    -0.81
    hemat
    -0.81
    ument
    -0.80
    PDF
    -0.79
    ictionary
    -0.75
    tel
    -0.74
    link
    -0.73
    Enlarge
    -0.72
    POSITIVE LOGITS
     inexper
    1.31
     inexperienced
    1.16
     rookies
    1.15
     teammates
    1.14
     injuries
    1.12
     teammate
    1.10
     rookie
    1.06
     Derrick
    1.01
    juries
    0.99
     Reggie
    0.95
    Activations Density 0.297%

    No Known Activations