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. 11-RES-JB
    6. 23373
    Prev
    Next
    INDEX
    Explanations

    predictions or projections about future events

    oai_token-act-pair · gpt-3.5-turbo

    future projections or estimates regarding people or events

    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
     Advertisement
    -0.68
    /+
    -0.67
    canon
    -0.66
    asin
    -0.62
     arrang
    -0.62
    rency
    -0.61
     Puzz
    -0.60
    ãĤ¦ãĤ¹
    -0.59
    ategory
    -0.59
    guards
    -0.59
    POSITIVE LOGITS
     perish
    1.20
     be
    1.18
     participate
    1.15
     flock
    1.12
     die
    1.12
     suffer
    1.12
     benefit
    1.09
     attend
    1.04
     converge
    1.00
     testify
    0.99
    Activations Density 0.196%

    No Known Activations