© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 3770
    Prev
    Next
    INDEX
    Explanations

    phrases related to exclusivity or uniqueness

    oai_token-act-pair · gpt-3.5-turbo

    the word "entirely" and its emphasis 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
    nings
    -0.75
    ITIES
    -0.68
    olester
    -0.68
    ulators
    -0.64
    hao
    -0.64
    ulative
    -0.64
    ITY
    -0.63
    Ñı
    -0.63
    ensis
    -0.62
    most
    -0.62
    POSITIVE LOGITS
     reliant
    0.84
     unsu
    0.83
     unrelated
    0.83
     predictable
    0.79
     fictitious
    0.79
     unexpl
    0.79
     different
    0.78
     subjective
    0.78
     optional
    0.78
     coinc
    0.78
    Activations Density 0.046%

    No Known Activations