© 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. 13368
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "ripped"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "sip" in different contexts

    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
     Palest
    -0.73
    é¾
    -0.70
     Siber
    -0.67
     Balanced
    -0.67
     Zed
    -0.66
     Vu
    -0.64
     Aval
    -0.64
     Nanto
    -0.64
    È
    -0.63
     DEN
    -0.62
    POSITIVE LOGITS
    ipping
    1.17
    ipped
    1.16
    insula
    1.00
    ips
    0.91
    olicy
    0.91
    avascript
    0.88
    psey
    0.88
    otle
    0.88
    etitive
    0.86
    ilant
    0.85
    Activations Density 0.004%

    No Known Activations