© 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. 1-RES-JB
    11. 9413
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating division or split between groups or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to division or separation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ECH
    -0.75
    rouse
    -0.75
     Waves
    -0.74
    ETS
    -0.72
    ORTS
    -0.72
    OD
    -0.71
    licks
    -0.70
    WARD
    -0.68
    ITNESS
    -0.67
     Gos
    -0.66
    POSITIVE LOGITS
     divided
    1.16
     divides
    0.90
     divide
    0.87
     dividing
    0.84
     divisions
    0.83
     divid
    0.80
     alleg
    0.76
     polarized
    0.76
     hypoc
    0.76
     split
    0.74
    Activations Density 0.009%

    No Known Activations