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. 832
    Prev
    Next
    INDEX
    Explanations

    the word "Despite" in texts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate contrast or contradiction

    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
    oided
    -0.82
    ANS
    -0.73
    culated
    -0.71
    ecycle
    -0.71
    rone
    -0.70
    ribe
    -0.69
    iaries
    -0.66
    area
    -0.66
    isa
    -0.65
    irez
    -0.65
    POSITIVE LOGITS
     assurances
    1.01
     setbacks
    1.01
     appearances
    1.00
     acknowledging
    0.98
     seeming
    0.95
     being
    0.92
     having
    0.91
     boasting
    0.91
     foregoing
    0.89
     warnings
    0.88
    Activations Density 0.058%

    No Known Activations