© 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. 18031
    Prev
    Next
    INDEX
    Explanations

    phrases containing reported speech or direct quotes

    oai_token-act-pair · gpt-3.5-turbo

    quotations and reported speech

    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
    £ı
    -0.96
    soDeliveryDate
    -0.89
    etheless
    -0.89
    ãĥij
    -0.87
    ļéĨĴ
    -0.80
    ¬¼
    -0.78
    ĵĺ
    -0.74
    rats
    -0.73
    ĪĴ
    -0.73
    ardless
    -0.71
    POSITIVE LOGITS
     says
    1.42
     said
    1.36
    said
    1.20
     recalls
    1.18
     admits
    1.16
     commented
    1.14
     remembers
    1.13
     explained
    1.12
     explains
    1.12
     joked
    1.11
    Activations Density 0.084%

    No Known Activations