© 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. 7826
    Prev
    Next
    INDEX
    Explanations

    phrases related to IPCC (Intergovernmental Panel on Climate Change) reports

    oai_token-act-pair · gpt-3.5-turbo

    references to the IPCC and related entities or reports

    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
    drive
    -0.83
    ker
    -0.79
    verb
    -0.78
    stop
    -0.77
    ening
    -0.74
    ucha
    -0.74
    kers
    -0.73
    actly
    -0.72
    vil
    -0.71
    blade
    -0.70
    POSITIVE LOGITS
    20439
    0.80
     Papers
    0.73
    oples
    0.70
     brim
    0.69
     IPCC
    0.68
     Protector
    0.68
    DragonMagazine
    0.67
    LEY
    0.66
     Browne
    0.66
    ciation
    0.66
    Activations Density 0.031%

    No Known Activations