© 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. 2-RES-JB
    11. 1442
    Prev
    Next
    INDEX
    Explanations

    descriptive words conveying a negative characteristic or feeling

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "nasty" and related negative descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HCR
    -0.85
    inet
    -0.83
    ingham
    -0.82
    inoa
    -0.76
    ETF
    -0.76
    aver
    -0.75
    produced
    -0.74
    inez
    -0.73
    oning
    -0.72
    Particip
    -0.72
    POSITIVE LOGITS
     nasty
    1.15
     surprises
    1.03
     adolesc
    1.02
     earthqu
    0.87
     spoil
    0.85
     ugly
    0.83
     undermin
    0.79
     poisonous
    0.79
     beasts
    0.77
     smelling
    0.77
    Activations Density 0.010%

    No Known Activations