© 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. 10856
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities/people associated with specific locations

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and groups, particularly in relation to Osama bin Laden and cultural backgrounds

    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
    neau
    -0.61
    -+-+
    -0.59
    Reviewed
    -0.58
    ources
    -0.57
     Turing
    -0.54
    alogue
    -0.51
     convict
    -0.49
    odder
    -0.49
    uve
    -0.49
     anonymously
    -0.49
    POSITIVE LOGITS
    nova
    0.79
    ahime
    0.71
    inki
    0.65
    uni
    0.64
    wei
    0.63
    Magikarp
    0.59
    ãĥŁ
    0.59
    oku
    0.58
    ulu
    0.57
    Pacific
    0.56
    Activations Density 0.920%

    No Known Activations