© 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. 13717
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific parts or areas within a larger whole

    oai_token-act-pair · gpt-3.5-turbo

    references to different components or aspects of a whole

    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
    terday
    -0.99
    ICO
    -0.89
    Ô
    -0.81
    ãĤ´ãĥ³
    -0.78
    oS
    -0.78
    aukee
    -0.77
    jriwal
    -0.75
     Rampage
    -0.72
    escription
    -0.70
     Rica
    -0.69
    POSITIVE LOGITS
     nearest
    0.86
     closest
    0.75
    osphere
    0.71
     least
    0.71
     furthe
    0.69
    lights
    0.67
     eyed
    0.60
     equivalent
    0.60
     tones
    0.59
     opposite
    0.58
    Activations Density 0.230%

    No Known Activations