© 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. 11-RES-JB
    11. 7148
    Prev
    Next
    INDEX
    Explanations

    sentences related to political and social ideologies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glim
    -1.16
     carbohyd
    -1.00
     nodd
    -0.93
     volunte
    -0.88
     gobl
    -0.88
     packing
    -0.85
     reluct
    -0.85
    soDeliveryDate
    -0.84
     creek
    -0.84
     freezer
    -0.84
    POSITIVE LOGITS
     Consequently
    1.41
     Indeed
    1.35
     Hence
    1.35
     Accordingly
    1.33
     Moreover
    1.32
     Thus
    1.31
     Such
    1.29
     Nevertheless
    1.27
     Yet
    1.27
     Suppose
    1.26
    Activations Density 0.310%

    No Known Activations