© 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. 3554
    Prev
    Next
    INDEX
    Explanations

    terms related to geological events or structural features

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to activities and classifications, particularly in the context of environmental, medical, and educational domains

    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
     Aval
    -0.51
    ortium
    -0.49
    irement
    -0.47
    ACTED
    -0.45
    cture
    -0.44
    DonaldTrump
    -0.44
    76561
    -0.43
     looph
    -0.42
    uckland
    -0.42
     AND
    -0.42
    POSITIVE LOGITS
     alike
    1.28
     versa
    0.88
     thereof
    0.82
     respectively
    0.80
     thereto
    0.64
    SPONSORED
    0.56
    cellaneous
    0.56
     accordingly
    0.53
     thereafter
    0.51
     equivalents
    0.50
    Activations Density 0.927%

    No Known Activations