© 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. 2-RES-JB
    11. 23305
    Prev
    Next
    INDEX
    Explanations

    phrases related to a connection or bond

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tie" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sburg
    -0.77
    hma
    -0.76
    tical
    -0.76
    Ïī
    -0.70
     Ignore
    -0.69
    ULE
    -0.67
    ocal
    -0.66
    olute
    -0.65
     Known
    -0.65
    angel
    -0.65
    POSITIVE LOGITS
    tie
    1.24
     tie
    1.22
    breaker
    0.95
     tying
    0.95
     ties
    0.95
     knot
    0.94
     tied
    0.89
    pipe
    0.89
     breaker
    0.84
    redo
    0.83
    Activations Density 0.011%

    No Known Activations