Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 17490
    Prev
    Next
    INDEX
    Explanations

    events or mentions related to climbing in a physical sense

    oai_token-act-pair · gpt-3.5-turbo

    references to climbing or climbers, particularly in a dramatic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REDACTED
    -0.80
    fold
    -0.74
     Gutenberg
    -0.68
    FORM
    -0.64
     Referred
    -0.63
    lihood
    -0.63
     inclusive
    -0.60
    NOW
    -0.58
    VERTIS
    -0.58
     Enterprise
    -0.58
    POSITIVE LOGITS
    pse
    1.27
    bers
    1.17
    ber
    1.16
    blers
    1.16
    ax
    1.14
    actic
    1.07
    atic
    1.07
    onial
    1.04
    bered
    1.03
    bling
    1.02
    Activations Density 0.050%

    No Known Activations