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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 1187
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating addition or inclusion

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "in addition to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dayName
    -0.79
    ANS
    -0.76
    soever
    -0.74
    blast
    -0.72
    irez
    -0.71
    Reviewer
    -0.71
    DOWN
    -0.70
    window
    -0.70
    enth
    -0.70
    rone
    -0.69
    POSITIVE LOGITS
     being
    1.04
     providing
    0.95
     benefiting
    0.93
     complying
    0.87
     ensuring
    0.83
     having
    0.83
     creating
    0.83
     helping
    0.82
     possessing
    0.82
     producing
    0.82
    Activations Density 0.061%

    No Known Activations