© 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. 22551
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and data

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    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
    selves
    -0.76
    wives
    -0.73
    ouses
    -0.72
    worms
    -0.72
     Shards
    -0.72
    mins
    -0.71
     Rohing
    -0.70
     Sins
    -0.69
     Gods
    -0.68
    loads
    -0.68
    POSITIVE LOGITS
     accessory
    0.85
     gadget
    0.83
     casualty
    0.83
     allied
    0.80
    advertising
    0.79
     tablet
    0.78
     courier
    0.77
     pedestrian
    0.77
    rogen
    0.76
     spectator
    0.75
    Activations Density 0.152%

    No Known Activations