© 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. 3984
    Prev
    Next
    INDEX
    Explanations

    words related to popular trends or terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "buzz."

    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
    izations
    -0.76
    isations
    -0.69
     dedication
    -0.68
    tein
    -0.68
     restitution
    -0.67
    ugal
    -0.65
    isation
    -0.65
    hibition
    -0.62
    ufact
    -0.62
    osaurs
    -0.62
    POSITIVE LOGITS
    saw
    1.34
    feed
    1.19
    arded
    1.05
    worthy
    1.04
    erd
    1.01
    words
    0.99
    er
    0.97
    ed
    0.96
    ards
    0.95
    oola
    0.91
    Activations Density 0.042%

    No Known Activations