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

    Neuronpedia

    APICircuit 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. 11-RES-JB
    6. 15596
    Prev
    Next
    INDEX
    Explanations

    phrases related to human suffering and injustice

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing suffering or hardship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isSpecialOrderable
    -0.93
     Activities
    -0.81
     GOODMAN
    -0.79
    vantage
    -0.77
     guiIcon
    -0.76
    \)
    -0.75
    ESE
    -0.74
     Frequency
    -0.74
    encers
    -0.74
    oward
    -0.74
    POSITIVE LOGITS
     rotting
    1.84
     decaying
    1.69
     lifeless
    1.63
     charred
    1.57
     barren
    1.52
     rotten
    1.48
     desolate
    1.47
     dise
    1.47
     crumbling
    1.45
     ruined
    1.41
    Activations Density 0.420%

    No Known Activations