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. 11-RES-JB
    6. 16912
    Prev
    Next
    INDEX
    Explanations

    adjectives related to steepness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to steepness or slope

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    blance
    -0.78
    ignty
    -0.70
    bers
    -0.68
    essage
    -0.66
    uve
    -0.65
    iverpool
    -0.65
    extra
    -0.64
    oreal
    -0.63
    ulhu
    -0.62
    umbn
    -0.61
    POSITIVE LOGITS
     slope
    1.12
     climb
    1.07
     uphill
    1.06
     slopes
    1.05
     ascent
    0.98
     staircase
    0.97
     gradient
    0.95
     incl
    0.94
     hill
    0.93
    ly
    0.92
    Activations Density 0.040%

    No Known Activations