© 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. 10434
    Prev
    Next
    INDEX
    Explanations

    terms related to specific types of issues, like water waste, food insecurity, budget cuts, identity fraud, ladder injuries, and future water shortages

    oai_token-act-pair · gpt-3.5-turbo

    terms related to resource allocation and social issues

    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
     Pace
    -0.73
    »Ĵ
    -0.71
    cale
    -0.70
    oscope
    -0.70
    redients
    -0.67
    thouse
    -0.65
    tml
    -0.63
    uits
    -0.63
    abase
    -0.63
     Alphabet
    -0.62
    POSITIVE LOGITS
     instability
    1.48
     failures
    1.44
     malf
    1.41
     disruptions
    1.39
     failure
    1.38
     disruption
    1.38
     disasters
    1.36
     insecurity
    1.36
     disturbances
    1.36
     deterioration
    1.34
    Activations Density 0.478%

    No Known Activations