© 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. 20285
    Prev
    Next
    INDEX
    Explanations

    references to dates

    oai_token-act-pair · gpt-3.5-turbo

    phrases or clauses containing commas, indicating lists or additional information

    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
    zn
    -0.65
    ARCH
    -0.63
    racuse
    -0.62
    enta
    -0.62
    SPA
    -0.61
     dreaming
    -0.58
    Local
    -0.56
     afar
    -0.56
     lucky
    -0.54
     liking
    -0.54
    POSITIVE LOGITS
     consists
    1.02
     revolves
    0.96
     consisted
    0.96
     contains
    0.95
     comprises
    0.95
     involves
    0.94
     represents
    0.93
     originated
    0.92
     is
    0.91
     illustrates
    0.89
    Activations Density 0.236%

    No Known Activations