© 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. 11978
    Prev
    Next
    INDEX
    Explanations

    mentions of accomplishments or achievements

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with competitive events or rankings

    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
    ãĥ©ãĥ³
    -0.48
    Eva
    -0.48
     unforgettable
    -0.47
     Dimension
    -0.46
     assorted
    -0.46
     Lithuan
    -0.45
    oso
    -0.45
     finally
    -0.45
    catentry
    -0.44
    ENGTH
    -0.43
    POSITIVE LOGITS
     anymore
    1.76
     nor
    1.71
    nor
    1.12
     whatsoever
    0.98
     slightest
    0.95
     anywhere
    0.95
     anything
    0.94
    yet
    0.94
     any
    0.93
     anybody
    0.91
    Activations Density 1.988%

    No Known Activations