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. 15082
    Prev
    Next
    INDEX
    Explanations

    body parts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sections or components of various subjects or contexts

    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
     Skies
    -0.68
     Arms
    -0.64
     commissions
    -0.59
     appropri
    -0.54
    balance
    -0.53
     affiliates
    -0.53
    stasy
    -0.53
    gently
    -0.53
     Leap
    -0.53
    berus
    -0.52
    POSITIVE LOGITS
    ials
    1.20
    icular
    1.12
    ridges
    1.12
    ridge
    1.11
    aking
    1.05
    iers
    0.99
    icularly
    0.96
    icle
    0.96
    isans
    0.95
     thereof
    0.93
    Activations Density 0.063%

    No Known Activations