© 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. 719
    Prev
    Next
    INDEX
    Explanations

    words related to intentions, plans, and causes

    oai_token-act-pair · gpt-3.5-turbo

    words related to ideologies and occupations

    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
     Dahl
    -0.64
     yak
    -0.62
     Sierra
    -0.61
     daylight
    -0.60
    DER
    -0.58
     Butt
    -0.57
     Kush
    -0.57
     Gad
    -0.57
     mist
    -0.57
     straw
    -0.57
    POSITIVE LOGITS
    ally
    2.50
    ality
    2.14
    als
    1.85
    alities
    1.79
    alist
    1.61
    ALLY
    1.55
    ative
    1.54
    al
    1.48
    ately
    1.47
    ationally
    1.47
    Activations Density 0.098%

    No Known Activations