© 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. 8-RES-JB
    11. 22501
    Prev
    Next
    INDEX
    Explanations

    phrases related to availability or release of products or services

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to product availability and features

    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
    enment
    -0.74
    ecd
    -0.73
    iddling
    -0.66
    emonic
    -0.66
    reated
    -0.65
     whiff
    -0.65
     supposed
    -0.64
    inventoryQuantity
    -0.64
    ghazi
    -0.63
    heit
    -0.63
    POSITIVE LOGITS
     tomorrow
    1.01
     soon
    0.83
     2019
    0.77
     tonight
    0.75
     concurrently
    0.72
     LIVE
    0.72
     2021
    0.71
     NX
    0.71
     hereafter
    0.71
     next
    0.70
    Activations Density 0.823%

    No Known Activations