© 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. 20265
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications or design features, especially with hyphenated words

    oai_token-act-pair · gpt-3.5-turbo

    elements related to digital content formats and design styles

    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
     Confederation
    -0.69
     MEN
    -0.69
     Ital
    -0.69
     Collins
    -0.67
     Afric
    -0.66
     Nass
    -0.65
     Fiscal
    -0.65
     Indigo
    -0.65
     Prob
    -0.64
     Meadows
    -0.64
    POSITIVE LOGITS
    esque
    1.68
    themed
    1.67
    inspired
    1.63
    style
    1.61
    based
    1.58
    derived
    1.52
    inducing
    1.51
    centric
    1.51
    like
    1.49
    driven
    1.47
    Activations Density 0.143%

    No Known Activations