© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18216
    Prev
    Next
    INDEX
    Explanations

    the word "another" followed by a noun

    oai_token-act-pair · gpt-3.5-turbo

    the word "another."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ãĥ©
    -0.63
    abin
    -0.62
    matic
    -0.57
    estone
    -0.56
    ses
    -0.55
    vec
    -0.55
    itta
    -0.55
    BF
    -0.55
    folk
    -0.54
    WE
    -0.54
    POSITIVE LOGITS
     another
    3.11
    another
    2.70
     Another
    1.96
    Another
    1.86
     others
    1.22
     somebody
    1.20
     someone
    1.15
     again
    1.06
     elsewhere
    1.05
     something
    1.00
    Activations Density 0.044%

    No Known Activations