© 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. 1-RES-JB
    11. 14102
    Prev
    Next
    INDEX
    Explanations

    references to the term "Rec." with numerical values, possibly indicating recommendations or recognition

    oai_token-act-pair · gpt-3.5-turbo

    references to recreational activities or the term 'Rec'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    furt
    -0.83
    MENTS
    -0.77
    tips
    -0.73
    OTH
    -0.71
    heid
    -0.69
    Magikarp
    -0.67
    à¼
    -0.65
     tong
    -0.65
    hammad
    -0.64
    MENT
    -0.63
    POSITIVE LOGITS
     Rec
    1.01
    ycle
    0.95
    urrent
    0.95
    ruit
    0.93
    onnaissance
    0.93
    ruits
    0.91
    oub
    0.86
    izoph
    0.83
    osponsors
    0.83
    inia
    0.83
    Activations Density 0.007%

    No Known Activations