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. 20604
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical positioning or location

    oai_token-act-pair · gpt-3.5-turbo

    spatial relationships and positioning in descriptions

    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
    Few
    -0.64
     Offline
    -0.62
     offline
    -0.62
    arcity
    -0.61
    ARS
    -0.61
    Reports
    -0.61
    Attempts
    -0.60
    Introduced
    -0.59
    MQ
    -0.59
    udi
    -0.58
    POSITIVE LOGITS
     the
    0.93
    neath
    0.93
     each
    0.87
     protr
    0.85
     underside
    0.80
     forehead
    0.80
     his
    0.79
     skull
    0.79
     your
    0.79
     hips
    0.78
    Activations Density 0.221%

    No Known Activations