© 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. 10-RES-JB
    11. 20562
    Prev
    Next
    INDEX
    Explanations

    specialized professions and areas of expertise, including lawyer, economist, attorney, ologist, consultant, expert, chef, and scientist

    oai_token-act-pair · gpt-3.5-turbo

    professions and their related titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.81
    Players
    -0.69
     Beasts
    -0.68
    thumbnails
    -0.65
     Players
    -0.63
    ouls
    -0.61
    ories
    -0.60
    enburg
    -0.60
    éĹĺ
    -0.60
    ombies
    -0.58
    POSITIVE LOGITS
     specializing
    1.38
     extraord
    1.11
     stationed
    0.93
     emer
    0.92
     who
    0.89
     whose
    0.88
     consultant
    0.86
     studying
    0.86
     residing
    0.85
     practicing
    0.85
    Activations Density 0.113%

    No Known Activations