Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 10534
    Prev
    Next
    INDEX
    Explanations

    specific characters followed by "hs" with varying levels of intensity

    oai_token-act-pair · gpt-3.5-turbo

    instances of high-frequency technical jargon or system errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.71
     Trojan
    -0.71
     convol
    -0.69
    tainment
    -0.68
     snail
    -0.67
    AUT
    -0.66
    FTWARE
    -0.63
    holding
    -0.63
    âĹ¼
    -0.63
    fman
    -0.61
    POSITIVE LOGITS
    hs
    1.26
    ubs
    1.11
    omed
    0.98
    ulhu
    0.96
    arah
    0.94
    ull
    0.93
    sein
    0.93
    oning
    0.92
    omes
    0.91
    achu
    0.91
    Activations Density 0.009%

    No Known Activations