© 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. 0-RES-JB
    11. 5334
    Prev
    Next
    INDEX
    Explanations

    specific references or terms in text

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms that indicate reference or citation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     captcha
    -0.66
    azaki
    -0.63
     tomorrow
    -0.60
     every
    -0.60
     tonight
    -0.54
     marrow
    -0.54
     free
    -0.53
    iven
    -0.52
     worthwhile
    -0.51
     ju
    -0.51
    POSITIVE LOGITS
     refers
    3.60
     refer
    2.07
     denotes
    2.04
     describes
    1.93
     referred
    1.81
     relates
    1.78
     implies
    1.75
     referring
    1.67
     specifies
    1.66
     translates
    1.65
    Activations Density 0.013%

    No Known Activations