© 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. 6-RES-JB
    11. 11953
    Prev
    Next
    INDEX
    Explanations

    instances of verbs related to actions or operations

    oai_token-act-pair · gpt-3.5-turbo

    instances of hacking and related technological vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itaire
    -0.65
    pex
    -0.58
     Doyle
    -0.57
    emale
    -0.56
    lished
    -0.55
    llah
    -0.54
    lance
    -0.54
    etheless
    -0.54
    jri
    -0.54
    aml
    -0.54
    POSITIVE LOGITS
     themselves
    0.88
     selves
    0.80
    MpServer
    0.70
    selves
    0.67
     orbits
    0.62
     mouths
    0.62
     helmets
    0.62
     coats
    0.59
     uniforms
    0.58
     necks
    0.57
    Activations Density 0.700%

    No Known Activations