© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 21728
    Prev
    Next
    INDEX
    Explanations

    references to or descriptions of physical objects like 'palm'

    oai_token-act-pair · gpt-3.5-turbo

    references to palm-related contexts and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eming
    -0.73
    NESS
    -0.73
    ski
    -0.71
    venants
    -0.71
    ROR
    -0.70
    OOL
    -0.70
    Else
    -0.68
     Hopkins
    -0.67
    definition
    -0.66
    eligible
    -0.66
    POSITIVE LOGITS
     palm
    1.30
     palms
    1.15
    istry
    0.83
     plantations
    0.78
     occas
    0.76
    itime
    0.75
     trees
    0.74
    ocene
    0.74
    rican
    0.74
    ieri
    0.73
    Activations Density 0.006%

    No Known Activations