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. 23617
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific names

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that appear to relate to timelines or numerical data

    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
     traveling
    -0.83
     tremend
    -0.79
     maneuver
    -0.77
     favors
    -0.74
     traveled
    -0.74
     favored
    -0.74
     favoring
    -0.72
     travelers
    -0.71
     maneu
    -0.71
     utilized
    -0.70
    POSITIVE LOGITS
    Labour
    1.21
    £
    1.01
    Britain
    1.00
    Austral
    1.00
    Liverpool
    1.00
    Scotland
    0.99
    BBC
    0.95
    England
    0.95
    Ireland
    0.95
    Firstly
    0.92
    Activations Density 0.410%

    No Known Activations