© 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. 22419
    Prev
    Next
    INDEX
    Explanations

    phrases describing an extreme level or limit of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate reaching an extreme situation or outcome

    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
    irm
    -0.74
    rounder
    -0.69
    annis
    -0.67
    thia
    -0.66
    ellow
    -0.64
    beit
    -0.62
    avorite
    -0.62
    irmed
    -0.61
    anus
    -0.61
    olly
    -0.61
    POSITIVE LOGITS
     where
    0.80
    liest
    0.79
    lessness
    0.77
     absurdity
    0.75
     brink
    0.75
     exhaustion
    0.71
    points
    0.70
     verge
    0.70
     point
    0.69
    ophys
    0.69
    Activations Density 0.029%

    No Known Activations