© 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. 4-RES-JB
    11. 14912
    Prev
    Next
    INDEX
    Explanations

    mentions of environmental protection and related policies and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to environmental regulations and clean air initiatives

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

    No Comments

    Negative Logits
    atars
    -0.72
    ANA
    -0.71
    ulu
    -0.71
    axter
    -0.70
    channelAvailability
    -0.69
    ãĥĥãĥī
    -0.69
    anova
    -0.66
    UA
    -0.65
    aez
    -0.65
    ãĥĥãĤ¯
    -0.64
    POSITIVE LOGITS
    iencies
    0.90
    estern
    0.79
     disinfect
    0.77
    ifice
    0.74
    posal
    0.68
     palate
    0.66
     Autob
    0.64
    lde
    0.63
     linen
    0.63
    clean
    0.61
    Activations Density 0.138%

    No Known Activations