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. 23351
    Prev
    Next
    INDEX
    Explanations

    words related to beds and bedrooms

    oai_token-act-pair · gpt-3.5-turbo

    references to beds and sleeping arrangements

    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
    arily
    -0.81
     Galile
    -0.63
     Voters
    -0.60
     CI
    -0.59
     Russo
    -0.59
     lockout
    -0.59
     disdain
    -0.58
    İĭ
    -0.57
     talents
    -0.56
     Mayweather
    -0.56
    POSITIVE LOGITS
    ding
    1.55
    ridden
    1.37
    spread
    1.35
    side
    1.26
    stead
    1.25
    sheets
    1.25
    lam
    1.23
    ded
    1.21
    sheet
    1.19
    fell
    1.12
    Activations Density 0.034%

    No Known Activations