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

    Neuronpedia

    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. 6-RES-JB
    11. 1496
    Prev
    Next
    INDEX
    Explanations

    words related to obstacles or challenges that need to be overcome

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "impact" or "important" situations

    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
    creen
    -0.77
    DragonMagazine
    -0.76
     GOODMAN
    -0.75
    hyde
    -0.71
     Lobby
    -0.68
     Alive
    -0.68
    RAFT
    -0.67
    \\\\\\\\
    -0.66
     Ribbon
    -0.66
    HCR
    -0.63
    POSITIVE LOGITS
    ossibly
    1.29
    romptu
    1.25
    regn
    1.24
    orter
    1.17
    orters
    1.16
    ressing
    1.14
    ulsive
    1.13
    urities
    1.11
    acet
    1.10
    otent
    1.08
    Activations Density 0.013%

    No Known Activations