Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 6861
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and related activities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rhy
    -0.84
     intrinsic
    -0.78
     structure
    -0.72
     gir
    -0.70
     whit
    -0.70
     unheard
    -0.70
     timet
    -0.70
     invari
    -0.70
     uncontroll
    -0.69
     tailor
    -0.68
    POSITIVE LOGITS
    Calif
    1.22
    Ohio
    1.18
    Minnesota
    1.18
    California
    1.17
    Florida
    1.17
    Michigan
    1.16
    Texas
    1.15
    Wisconsin
    1.14
    Washington
    1.13
    Fla
    1.12
    Activations Density 0.027%

    No Known Activations