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. 7-RES-JB
    6. 16347
    Prev
    Next
    INDEX
    Explanations

    words related to verticality or directions like up and down

    oai_token-act-pair · gpt-3.5-turbo

    references to vertical alignment or orientation

    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
    keeper
    -0.91
    giving
    -0.88
    keeping
    -0.86
    REDACTED
    -0.84
    keepers
    -0.83
    unes
    -0.77
    ptives
    -0.75
    ãģ¦
    -0.75
    mberg
    -0.75
     [&
    -0.74
    POSITIVE LOGITS
     axis
    0.97
     dimension
    0.94
     stabil
    0.90
     ascent
    0.90
     dimensions
    0.86
     takeoff
    0.85
     velocity
    0.85
     vertical
    0.85
     integration
    0.85
     stripes
    0.83
    Activations Density 0.020%

    No Known Activations