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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14111
    Prev
    Next
    INDEX
    Explanations

    words related to controversial issues or topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political and social issues

    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
    MM
    -0.77
    DOS
    -0.74
    amaz
    -0.67
    ipel
    -0.64
    atorium
    -0.63
    mie
    -0.63
    antam
    -0.62
    icz
    -0.62
    enko
    -0.61
    owicz
    -0.61
    POSITIVE LOGITS
     imaginable
    1.04
     relating
    0.85
     involving
    0.82
     such
    0.77
     pertaining
    0.72
     perceived
    0.71
     deemed
    0.69
     like
    0.69
     affecting
    0.68
     ranging
    0.68
    Activations Density 0.854%

    No Known Activations