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. 9704
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive forms

    oai_token-act-pair · gpt-3.5-turbo

    the repeated character "ľ" in various 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
     sugg
    -0.86
     carbohyd
    -0.83
     spir
    -0.82
     synerg
    -0.82
     accomp
    -0.81
     favor
    -0.80
     enriched
    -0.77
     reflex
    -0.75
     satell
    -0.75
     rul
    -0.73
    POSITIVE LOGITS
    Because
    1.47
    Secondly
    1.38
    One
    1.36
    If
    1.35
    What
    1.34
    Sometimes
    1.34
    It
    1.33
    There
    1.33
    Originally
    1.33
    When
    1.32
    Activations Density 0.118%

    No Known Activations