© 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. 15489
    Prev
    Next
    INDEX
    Explanations

    phrases related to problems or struggles

    oai_token-act-pair · gpt-3.5-turbo

    recurring themes of crises and financial concerns

    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
    urch
    -0.68
    owered
    -0.66
    anchester
    -0.62
     seiz
    -0.61
     newcomer
    -0.61
    Su
    -0.60
    ovember
    -0.59
    ower
    -0.59
    Interested
    -0.58
    wan
    -0.58
    POSITIVE LOGITS
     blah
    0.96
    whatever
    0.92
    tics
    0.77
    !--
    0.76
    -|
    0.70
     damned
    0.65
    etc
    0.64
    bats
    0.63
     drums
    0.63
     ANGEL
    0.63
    Activations Density 0.973%

    No Known Activations