© 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. 11-RES-JB
    11. 18800
    Prev
    Next
    INDEX
    Explanations

    the word "because" within sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal beliefs and character evaluations

    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
    ï¸ı
    -0.96
    âĢ
    -0.95
    ðŁij
    -0.91
    âķIJ
    -0.87
    âĸ
    -0.87
    spons
    -0.86
    à¼
    -0.80
    ðŁ
    -0.79
     âľĶ
    -0.79
    -0.78
    POSITIVE LOGITS
     Freud
    1.30
     Nietzsche
    1.28
     Shakespeare
    1.20
     Socrates
    1.18
     Kissinger
    1.11
     Kubrick
    1.11
     Elvis
    1.09
     Dickens
    1.08
     Einstein
    1.08
     Gandhi
    1.07
    Activations Density 0.956%

    No Known Activations