© 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. 6042
    Prev
    Next
    INDEX
    Explanations

    specific university names and years

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical data and years

    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
     rall
    -0.72
     gorge
    -0.66
     conduc
    -0.64
     pedals
    -0.63
     seiz
    -0.62
     brace
    -0.60
     sandwiches
    -0.60
    pport
    -0.59
     spons
    -0.58
     organising
    -0.57
    POSITIVE LOGITS
    ļéĨĴ
    1.01
     Ibid
    0.91
    igible
    0.69
     Meyer
    0.68
    EStream
    0.68
    illary
    0.67
    lucent
    0.66
    DragonMagazine
    0.66
     Pew
    0.64
     Collection
    0.63
    Activations Density 0.421%

    No Known Activations