© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 6041
    Prev
    Next
    INDEX
    Explanations

    names of people and maybe co-authors of scholarly works

    oai_token-act-pair · gpt-3.5-turbo

    references to authors and contributors in scholarly works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resil
    -0.57
     puppies
    -0.55
     disrespect
    -0.53
     bathrooms
    -0.53
     surrounded
    -0.51
    regulated
    -0.51
     successors
    -0.50
     partying
    -0.50
     discriminated
    -0.50
     suites
    -0.50
    POSITIVE LOGITS
     Shapiro
    0.81
     Schro
    0.80
     Barrett
    0.78
     Thompson
    0.77
     Doyle
    0.77
     Levin
    0.76
     McCl
    0.76
     McC
    0.75
     McK
    0.75
     Nolan
    0.75
    Activations Density 0.390%

    No Known Activations