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. 19276
    Prev
    Next
    INDEX
    Explanations

    mentions of buildings or structures being constructed or built

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "built" in various contexts related to construction

    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
    Published
    -0.69
     Translation
    -0.69
     Fren
    -0.62
    Reviewer
    -0.60
    Charges
    -0.59
    ãĥ´
    -0.59
    Food
    -0.58
    phas
    -0.57
     Editors
    -0.57
    lations
    -0.57
    POSITIVE LOGITS
     atop
    1.06
     around
    0.94
     cheaply
    0.91
     into
    0.91
     upon
    0.85
     entirely
    0.82
     using
    0.81
     onto
    0.79
     anew
    0.78
     circa
    0.78
    Activations Density 0.043%

    No Known Activations