© 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. 9-RES-JB
    11. 6137
    Prev
    Next
    INDEX
    Explanations

    terms related to significant or key individuals or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to roles and positions of power or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obal
    -0.77
    izoph
    -0.74
    anium
    -0.74
    ©¶æ
    -0.73
    Ãį
    -0.72
    Balt
    -0.72
    iolet
    -0.70
    avia
    -0.70
    ãģį
    -0.68
    area
    -0.68
    POSITIVE LOGITS
     extraord
    1.35
     mascot
    0.70
    glers
    0.68
     liar
    0.67
     alike
    0.67
     Saban
    0.65
     litter
    0.64
     grin
    0.64
     archetype
    0.64
     dangling
    0.63
    Activations Density 0.379%

    No Known Activations