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. 6-RES-JB
    6. 1865
    Prev
    Next
    INDEX
    Explanations

    mentions related to climbing activities or climbers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to climbing or climbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REDACTED
    -0.91
    fold
    -0.80
     Mour
    -0.73
     Gutenberg
    -0.72
    Ô
    -0.69
    landish
    -0.68
    VERTIS
    -0.68
     Referred
    -0.67
     inclusive
    -0.64
    FORM
    -0.64
    POSITIVE LOGITS
    atically
    1.00
    actic
    0.97
    atic
    0.97
    ber
    0.96
    bers
    0.96
    ician
    0.90
    pse
    0.90
    acter
    0.90
    bled
    0.89
    atography
    0.88
    Activations Density 0.028%

    No Known Activations