© 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. 15747
    Prev
    Next
    INDEX
    Explanations

    words related to accusations or legal terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to accounts or accreditation

    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
    SG
    -0.62
     Keynes
    -0.62
     Sawyer
    -0.62
     dare
    -0.59
    SHIP
    -0.59
    bush
    -0.58
     fundamentally
    -0.57
     shed
    -0.57
    culosis
    -0.57
    çīĪ
    -0.56
    POSITIVE LOGITS
    reditation
    1.55
    ompl
    1.54
    redited
    1.47
    ommod
    1.46
    idental
    1.42
    urate
    1.36
    uracy
    1.36
    identally
    1.35
    ords
    1.30
    ursed
    1.29
    Activations Density 0.020%

    No Known Activations