© 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. 1-RES-JB
    11. 959
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing individuality or importance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "special."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Twain
    -0.79
     =====
    -0.71
    xxx
    -0.69
     Tib
    -0.67
    Unknown
    -0.66
    ·
    -0.65
    VO
    -0.64
    åħī
    -0.63
    Wa
    -0.62
    âĢł
    -0.62
    POSITIVE LOGITS
    ised
    1.11
    ties
    0.95
    ombat
    0.88
    isable
    0.86
    isations
    0.86
    isal
    0.86
    isbury
    0.85
    atural
    0.83
    FTWARE
    0.82
     special
    0.82
    Activations Density 0.018%

    No Known Activations