© 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. 9-RES-JB
    11. 13257
    Prev
    Next
    INDEX
    Explanations

    words related to criticism and comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditions or attributes associated with objects or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bell
    -0.67
    learning
    -0.65
    ciation
    -0.64
    atform
    -0.64
    reci
    -0.63
    stice
    -0.63
    break
    -0.63
    ById
    -0.61
    Break
    -0.61
    0002
    -0.61
    POSITIVE LOGITS
     characterize
    1.03
     plague
    0.95
     normally
    0.86
     traditionally
    0.85
     prevailed
    0.85
     typical
    0.79
     characterized
    0.79
     ordinarily
    0.79
     predecessors
    0.78
     traditional
    0.78
    Activations Density 0.183%

    No Known Activations