© 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. 7-RES-JB
    11. 18615
    Prev
    Next
    INDEX
    Explanations

    phrases describing the comparison or degree of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating degrees of comparison or contrasting quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -1.02
    ividual
    -0.76
    enaries
    -0.71
    naires
    -0.71
    ulus
    -0.70
    çīĪ
    -0.70
     Awakens
    -0.69
    rosis
    -0.68
     throats
    -0.68
     Turns
    -0.67
    POSITIVE LOGITS
     unlikely
    1.00
     evident
    0.98
     likely
    0.96
     dependent
    0.95
     accurate
    0.95
     prevalent
    0.95
     reliant
    0.92
     important
    0.92
     feasible
    0.92
     indicative
    0.91
    Activations Density 0.295%

    No Known Activations