© 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. 6-RES-JB
    11. 17804
    Prev
    Next
    INDEX
    Explanations

    mentions related to a specific online community or platform

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific character or entity, likely in a gaming context

    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
    eering
    -1.07
    eers
    -1.03
    Downloadha
    -0.92
    eer
    -0.84
    xon
    -0.80
    pection
    -0.66
    ktop
    -0.65
    Interstitial
    -0.65
    Versions
    -0.63
    ça
    -0.63
    POSITIVE LOGITS
    istics
    0.93
    ying
    0.83
    estone
    0.83
    actic
    0.77
    ifier
    0.76
    TL
    0.76
    orem
    0.75
    outing
    0.75
    itus
    0.75
    oward
    0.75
    Activations Density 0.024%

    No Known Activations