© 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. 11-RES-JB
    11. 20547
    Prev
    Next
    INDEX
    Explanations

    the word "attempt" or similar words inferring trying to do something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "attempt" and its variants

    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
     Angola
    -0.64
     Wrap
    -0.58
     Senegal
    -0.54
     Blend
    -0.52
     Inspector
    -0.51
    ranging
    -0.51
     Apostle
    -0.51
    embed
    -0.51
    LLOW
    -0.51
    eyes
    -0.50
    POSITIVE LOGITS
    Attempts
    0.96
     unsuccessfully
    0.87
     to
    0.84
    ramid
    0.77
    bles
    0.77
    nir
    0.75
     attempts
    0.74
     attempt
    0.72
    ãĥĺ
    0.70
    llor
    0.69
    Activations Density 0.051%

    No Known Activations