© 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. 1-RES-JB
    11. 23563
    Prev
    Next
    INDEX
    Explanations

    mentions of politicians from California

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VK
    -0.70
    ty
    -0.66
     Grail
    -0.66
     CMS
    -0.65
    clock
    -0.60
    lift
    -0.60
     Drawn
    -0.59
     HIP
    -0.58
    ebin
    -0.58
     Hussain
    -0.58
    POSITIVE LOGITS
    Calif
    1.24
    ignt
    0.92
    sylvania
    0.87
    utics
    0.80
    luent
    0.79
    ortium
    0.79
    aii
    0.77
     Calif
    0.75
     Californ
    0.74
    qua
    0.72
    Activations Density 0.007%

    No Known Activations