© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 24483
    Prev
    Next
    INDEX
    Explanations

    mentions of business activities and operations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to regulations and industry practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.74
    _-
    -0.66
     {*
    -0.65
    ļéĨĴ
    -0.64
     guiIcon
    -0.58
     livest
    -0.56
    later
    -0.56
    »Ĵ
    -0.53
     secondly
    -0.53
    anwhile
    -0.52
    POSITIVE LOGITS
     themselves
    0.90
     their
    0.83
    their
    0.75
     cryptocurrencies
    0.68
     THEIR
    0.67
    selves
    0.67
     cryptocurrency
    0.64
     Their
    0.63
     theirs
    0.62
    tackle
    0.59
    Activations Density 1.065%

    No Known Activations