© 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. 11865
    Prev
    Next
    INDEX
    Explanations

    phrases related to news reports or stories

    oai_token-act-pair · gpt-3.5-turbo

    references to news stories and reports

    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
    unts
    -0.72
    */(
    -0.71
    ophers
    -0.71
    wake
    -0.71
     philos
    -0.69
    ometry
    -0.69
    ikarp
    -0.69
     palate
    -0.67
     joystick
    -0.67
    ertodd
    -0.67
    POSITIVE LOGITS
     Murdoch
    0.90
     sensational
    0.82
    essler
    0.79
    reporting
    0.78
    reports
    0.76
     reports
    0.76
    Narr
    0.76
     articles
    0.75
     spreads
    0.75
     portrays
    0.74
    Activations Density 0.140%

    No Known Activations