© 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. 6-RES-JB
    11. 335
    Prev
    Next
    INDEX
    Explanations

    names containing the substring "ve"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¥µ
    -0.67
    illance
    -0.67
    igators
    -0.67
    direction
    -0.67
    upuncture
    -0.65
    izoph
    -0.65
    href
    -0.64
    stanbul
    -0.62
    igator
    -0.61
    dict
    -0.61
    POSITIVE LOGITS
     Robinson
    1.05
     McKay
    1.00
     Michaels
    0.99
     Richards
    0.98
     Coleman
    0.98
     Farrell
    0.98
     Ryder
    0.97
     Peters
    0.96
     McCull
    0.95
     Cumm
    0.94
    Activations Density 0.215%

    No Known Activations