© 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. 10260
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic and societal changes

    oai_token-act-pair · gpt-3.5-turbo

    patterns or trends in data and social behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    their
    -0.86
     Their
    -0.86
    Their
    -0.79
     THEIR
    -0.79
     They
    -0.71
     their
    -0.70
    imeter
    -0.69
    They
    -0.65
    avanaugh
    -0.63
     themselves
    -0.62
    POSITIVE LOGITS
     favour
    0.95
     organisations
    0.90
     travellers
    0.85
     organisers
    0.84
     whilst
    0.80
     neighbourhoods
    0.79
     Britons
    0.78
     behaviours
    0.77
     realised
    0.77
     labou
    0.76
    Activations Density 1.024%

    No Known Activations