© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23684
    Prev
    Next
    INDEX
    Explanations

    phrases related to exacerbating or worsening existing situations

    oai_token-act-pair · gpt-3.5-turbo

    repetitive references to the definite article "the" in various contexts

    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
    replace
    -0.77
     namely
    -0.76
     besides
    -0.70
     overseen
    -0.68
    rand
    -0.68
     alone
    -0.68
    tackle
    -0.67
    usa
    -0.67
     presided
    -0.65
     wherein
    -0.65
    POSITIVE LOGITS
     entirety
    1.17
     entire
    1.15
     remainder
    1.06
     effectiveness
    1.05
     possibility
    1.04
     latter
    1.03
     notion
    1.02
    ses
    1.00
     outcome
    1.00
     extent
    0.98
    Activations Density 0.317%

    No Known Activations