© 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. 6-RES-JB
    11. 1662
    Prev
    Next
    INDEX
    Explanations

    phrases related to the GS (General Schedule) system used in the United States government

    oai_token-act-pair · gpt-3.5-turbo

    references to specific models or types of technology related to GS (Game Score)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ications
    -0.94
    icating
    -0.85
    icates
    -0.84
    iating
    -0.84
    jad
    -0.79
    icative
    -0.79
    ous
    -0.73
    acles
    -0.73
    ique
    -0.71
    ively
    -0.68
    POSITIVE LOGITS
    earch
    1.02
    IFT
    0.99
    OURCE
    0.86
    ngth
    0.82
    ffiti
    0.75
    avage
    0.74
    OUND
    0.72
    atellite
    0.72
    ORGE
    0.71
    YS
    0.70
    Activations Density 0.043%

    No Known Activations