© 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. 0-RES-JB
    11. 16434
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'pin'

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oath
    -0.77
     Ethics
    -0.76
    ersed
    -0.76
     Oversight
    -0.75
    ales
    -0.73
    kj
    -0.71
    venant
    -0.70
    etics
    -0.70
    ctuary
    -0.69
    bnb
    -0.68
    POSITIVE LOGITS
     pin
    3.66
     pins
    2.79
    Pin
    2.41
     Pin
    2.32
    pin
    2.14
     pinned
    1.98
    PIN
    1.78
    pins
    1.69
     PIN
    1.66
     Pinball
    1.32
    Activations Density 0.014%

    No Known Activations