© 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. 11-RES-JB
    11. 23039
    Prev
    Next
    INDEX
    Explanations

    phrases related to contradicting statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to contradictions or contradictory evidence

    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
     tyres
    -0.50
     civilisation
    -0.48
     unemploy
    -0.46
     rubbish
    -0.46
     tyre
    -0.44
     organise
    -0.44
     Gaddafi
    -0.43
     prostitution
    -0.43
     hemp
    -0.42
     unlaw
    -0.42
    POSITIVE LOGITS
    âĢ
    1.26
     âĢ
    0.99
    ãĢ
    0.91
    .—
    0.88
    ¶
    0.84
    âĢ¢âĢ¢
    0.83
    ––
    0.82
    âĢł
    0.82
    âģ
    0.81
    ÂŃ
    0.81
    Activations Density 1.862%

    No Known Activations