© 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. 0-RES-JB
    11. 16447
    Prev
    Next
    INDEX
    Explanations

    words related to political events or social issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "$:/
    -0.70
     affiliation
    -0.63
     connection
    -0.62
     radiant
    -0.61
    OTO
    -0.60
     overturn
    -0.60
     FANTASY
    -0.59
     Â
    -0.59
     neutral
    -0.58
     appe
    -0.58
    POSITIVE LOGITS
    ums
    4.81
    um
    2.21
    UM
    1.90
    ummies
    1.36
    ummy
    1.31
    umn
    1.31
    umps
    1.22
    ummer
    1.22
    umb
    1.15
    umm
    1.15
    Activations Density 0.008%

    No Known Activations