© 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. 6559
    Prev
    Next
    INDEX
    Explanations

    phrases related to contrasting good and bad situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that compare positive and negative aspects

    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
    eters
    -0.82
     veins
    -0.73
    agne
    -0.71
    sbm
    -0.70
    rontal
    -0.68
    inez
    -0.68
    artment
    -0.67
    iard
    -0.66
    quit
    -0.66
    ttes
    -0.66
    POSITIVE LOGITS
     brightest
    0.94
     Powerful
    0.81
     bad
    0.79
     prosperous
    0.79
     evil
    0.78
     honorable
    0.77
    Evil
    0.75
     indifferent
    0.75
     mighty
    0.74
     equitable
    0.74
    Activations Density 0.197%

    No Known Activations