© 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. 13482
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to negative effects or consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to negative effects or reactions

    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
    rod
    -0.79
    swick
    -0.75
    src
    -0.74
    liam
    -0.72
    ynthesis
    -0.72
    ramid
    -0.71
    elf
    -0.71
    chen
    -0.71
     Kinnikuman
    -0.71
    adr
    -0.70
    POSITIVE LOGITS
     adverse
    1.08
     undermin
    0.95
     consequences
    0.91
     consequence
    0.88
     effects
    0.86
     impacts
    0.82
     publicity
    0.82
     outcomes
    0.80
     Downs
    0.77
     affect
    0.77
    Activations Density 0.010%

    No Known Activations