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. 7134
    Prev
    Next
    INDEX
    Explanations

    occurrences of actions being taken or events happening

    oai_token-act-pair · gpt-3.5-turbo

    references to formal announcements or documents related to events or gatherings

    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
     Units
    -0.89
     Gleaming
    -0.77
     acquisitions
    -0.74
     transformations
    -0.72
     Numbers
    -0.71
     Levels
    -0.71
     Monsters
    -0.70
     fractions
    -0.69
     Passive
    -0.69
     verbs
    -0.68
    POSITIVE LOGITS
    ritten
    0.92
    itialized
    0.91
    agraph
    0.83
    pload
    0.82
     underway
    0.80
    emaker
    0.78
    ugi
    0.78
    ģ«
    0.76
    berra
    0.76
     ensued
    0.75
    Activations Density 0.462%

    No Known Activations