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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20499
    Prev
    Next
    INDEX
    Explanations

    terms related to legal processes or investigative activities

    oai_token-act-pair · gpt-3.5-turbo

    key terms and concepts related to processes and structures

    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
    usalem
    -0.71
    aughtered
    -0.68
    ushes
    -0.66
    etsk
    -0.65
    venient
    -0.62
     Jol
    -0.61
    olulu
    -0.61
    ahoo
    -0.60
    oops
    -0.56
    delete
    -0.56
    POSITIVE LOGITS
     outweigh
    0.83
     versus
    0.81
    Reviewer
    0.78
     depends
    0.78
    Interstitial
    0.72
     compared
    0.72
     depended
    0.71
     itself
    0.70
     varies
    0.68
     relative
    0.66
    Activations Density 0.669%

    No Known Activations