© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 10209
    Prev
    Next
    INDEX
    Explanations

    prepositions along with objects of actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating locations or positions associated with actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RAG
    -0.72
    ãĤ¢ãĥ«
    -0.70
    Connector
    -0.68
    çĶ°
    -0.67
    NES
    -0.67
    âĸij
    -0.66
    OV
    -0.66
    ãĥĪ
    -0.66
    ICA
    -0.65
    avia
    -0.64
    POSITIVE LOGITS
     various
    0.87
     unsuspecting
    0.82
     imitation
    0.71
     themselves
    0.71
     behalf
    0.70
     fictitious
    0.68
     settlements
    0.67
     remote
    0.66
     impunity
    0.65
     makeshift
    0.64
    Activations Density 0.550%

    No Known Activations