© 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. 6-RES-JB
    11. 2611
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "cherry."

    oai_token-act-pair · gpt-3.5-turbo

    references to cherries and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matic
    -0.96
    acial
    -0.90
    restling
    -0.87
    emic
    -0.80
    ikarp
    -0.79
    ensive
    -0.79
    matically
    -0.70
    scan
    -0.70
    runner
    -0.69
    mable
    -0.68
    POSITIVE LOGITS
    bourg
    0.93
    creen
    0.87
    éĹĺ
    0.86
     Blossom
    0.83
     cherry
    0.81
    obyl
    0.75
     bloss
    0.74
    area
    0.73
    onne
    0.69
    acters
    0.68
    Activations Density 0.063%

    No Known Activations