© 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. 1-RES-JB
    11. 3355
    Prev
    Next
    INDEX
    Explanations

    words related to negative qualities or traits

    oai_token-act-pair · gpt-3.5-turbo

    Negative descriptors related to unpleasantness or harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inet
    -0.86
    ingham
    -0.85
    inoa
    -0.81
    HCR
    -0.79
    produced
    -0.76
    inez
    -0.75
    particip
    -0.74
    issued
    -0.73
    ination
    -0.73
    Particip
    -0.73
    POSITIVE LOGITS
     nasty
    1.25
     earthqu
    0.97
     adolesc
    0.96
     surprises
    0.94
     ugly
    0.87
     spoil
    0.85
     barb
    0.83
     poisonous
    0.77
     beasts
    0.76
     mud
    0.76
    Activations Density 0.007%

    No Known Activations