© 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. 3-RES-JB
    11. 13562
    Prev
    Next
    INDEX
    Explanations

    phrases related to tracking and monitoring

    oai_token-act-pair · gpt-3.5-turbo

    references to tracking and maintaining progress or status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ALLY
    -0.75
    inals
    -0.71
    lot
    -0.69
    MAL
    -0.68
    Latin
    -0.65
    ELY
    -0.63
    ĪĴ
    -0.62
    ESA
    -0.61
    COLOR
    -0.61
    IER
    -0.61
    POSITIVE LOGITS
     afloat
    0.73
     footing
    0.69
     tight
    0.68
     wraps
    0.68
     entertained
    0.67
     steady
    0.67
    emy
    0.65
     productive
    0.64
     indefinitely
    0.63
    readable
    0.63
    Activations Density 0.293%

    No Known Activations