© 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. 18592
    Prev
    Next
    INDEX
    Explanations

    phrases introducing or explaining concepts or ideas

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating consequences, benefits, or explanations in a discussion

    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
    eric
    -0.68
    onics
    -0.62
    hell
    -0.60
    psc
    -0.59
    onement
    -0.58
    raphic
    -0.58
    lems
    -0.57
    raid
    -0.56
    borg
    -0.56
    ppers
    -0.55
    POSITIVE LOGITS
     involves
    0.87
     relates
    0.85
     overlooked
    0.85
     limitation
    0.77
     includes
    0.75
     arises
    0.74
     excludes
    0.73
     pecul
    0.71
     contributing
    0.70
     distinguishes
    0.70
    Activations Density 0.142%

    No Known Activations