© 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. 10-RES-JB
    11. 6414
    Prev
    Next
    INDEX
    Explanations

    words related to social and political ideologies or movements

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of discrimination and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whilst
    -0.77
     Secondly
    -0.74
     Firstly
    -0.73
     realise
    -0.72
     secondly
    -0.68
    é¾įå
    -0.67
     '.
    -0.67
    Firstly
    -0.65
     realised
    -0.59
     honour
    -0.59
    POSITIVE LOGITS
    ,
    1.08
    ,...
    0.98
    *,
    0.79
     and
    0.71
    ,[
    0.70
    .,
    0.70
    !,
    0.69
     etc
    0.68
    +,
    0.68
    -,
    0.64
    Activations Density 0.444%

    No Known Activations