© 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. 11-RES-JB
    11. 4879
    Prev
    Next
    INDEX
    Explanations

    terms related to urban environments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to public systems and community issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.83
     AND
    -0.73
     or
    -0.58
     et
    -0.56
    and
    -0.53
     And
    -0.53
     Aval
    -0.50
    tty
    -0.50
     looph
    -0.46
     inh
    -0.46
    POSITIVE LOGITS
     alike
    1.20
     thereof
    1.01
     versa
    0.86
     thereto
    0.85
    axter
    0.76
    sequent
    0.69
    cellaneous
    0.69
    SPONSORED
    0.66
     consequ
    0.65
     accordingly
    0.65
    Activations Density 0.819%

    No Known Activations