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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 12966
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific topics or arguments discussed in various articles

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guessing
    -0.69
     Riding
    -0.62
     Possible
    -0.60
    ãĥ¬
    -0.59
     Oliv
    -0.59
     Charg
    -0.58
     cuff
    -0.58
     Breat
    -0.57
    Charg
    -0.57
     Dro
    -0.57
    POSITIVE LOGITS
     resulted
    1.00
     spans
    0.96
     culminated
    0.96
     accompanies
    0.93
     exceeds
    0.91
     originated
    0.91
     preceded
    0.91
     perme
    0.90
     arose
    0.88
    ļéĨĴ
    0.87
    Activations Density 0.280%

    No Known Activations