Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 19147
    Prev
    Next
    INDEX
    Explanations

    adjectives describing the emotional impact of situations or events

    oai_token-act-pair · gpt-3.5-turbo

    words that express strong emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ournal
    -0.64
     polymorph
    -0.64
    uclear
    -0.63
    ibliography
    -0.61
    ighth
    -0.61
    eely
    -0.60
    tein
    -0.60
    cipl
    -0.59
     broom
    -0.59
     matured
    -0.59
    POSITIVE LOGITS
     enough
    1.01
     XD
    0.84
    LY
    0.79
    ãĤ´
    0.77
     because
    0.73
     Enough
    0.73
     nonetheless
    0.70
     Hond
    0.69
    nell
    0.66
    ciating
    0.66
    Activations Density 0.211%

    No Known Activations