© 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. 0-RES-JB
    11. 1187
    Prev
    Next
    INDEX
    Explanations

    djectives describing extreme or superlative qualities

    oai_token-act-pair · gpt-3.5-turbo

    adjectives describing extreme conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cale
    -0.81
    PAC
    -0.72
    iership
    -0.72
    matter
    -0.70
    emouth
    -0.69
    iform
    -0.69
    arget
    -0.69
    bourg
    -0.68
    ensive
    -0.68
    abase
    -0.67
    POSITIVE LOGITS
     dri
    1.17
    ~
    1.13
    Ĥİ
    0.90
    yss
    0.64
     Yi
    0.64
     Crus
    0.63
     flames
    0.62
     Ezra
    0.61
     gust
    0.61
     Guinness
    0.61
    Activations Density 0.000%

    No Known Activations