© 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
    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. 836
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal opinions and attributes

    oai_token-act-pair · gpt-3.5-turbo

    co-occurrence of the word "and" with various other terms

    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
    fell
    -0.83
    ocument
    -0.75
    ogether
    -0.73
    wark
    -0.72
    oti
    -0.70
    opol
    -0.69
    YC
    -0.69
    uta
    -0.69
    enth
    -0.68
    arte
    -0.67
    POSITIVE LOGITS
     ample
    1.31
     minimal
    1.21
     abundant
    1.20
     lousy
    1.15
     negligible
    1.12
     impecc
    1.08
     plenty
    1.08
     excellent
    1.08
     generous
    1.08
     plentiful
    1.08
    Activations Density 0.345%

    No Known Activations