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. 20546
    Prev
    Next
    INDEX
    Explanations

    sentences that express personal opinions and feelings

    oai_token-act-pair · gpt-3.5-turbo

    expressions of subjective opinions or feelings about various topics

    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
    asus
    -0.70
    ICA
    -0.67
    minus
    -0.66
    idth
    -0.66
    ãĤº
    -0.65
    anyon
    -0.64
     Nationals
    -0.64
    afia
    -0.63
    yx
    -0.62
    eday
    -0.62
    POSITIVE LOGITS
     amusing
    1.51
     fascinating
    1.45
     objectionable
    1.36
     irresistible
    1.34
     interesting
    1.34
     hilarious
    1.32
     intriguing
    1.32
     attractive
    1.31
     appealing
    1.31
     helpful
    1.30
    Activations Density 0.138%

    No Known Activations