© 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. 6825
    Prev
    Next
    INDEX
    Explanations

    references to award-winning accomplishments or individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to award-winning accomplishments in various fields

    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
    seless
    -0.81
    adas
    -0.76
    thia
    -0.70
    Īè
    -0.65
    adra
    -0.65
    aucuses
    -0.65
     semblance
    -0.65
    idon
    -0.65
    rir
    -0.64
    olen
    -0.64
    POSITIVE LOGITS
     author
    1.01
     novelist
    0.96
     actress
    0.95
     journalist
    0.89
     Pulitzer
    0.84
     writer
    0.82
     poet
    0.82
     composer
    0.80
     artist
    0.79
     filmmaker
    0.79
    Activations Density 0.089%

    No Known Activations