© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20459
    Prev
    Next
    INDEX
    Explanations

    technical terms related to geology and physical sciences

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to tectonics and geoscience concepts

    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
    PDATE
    -0.73
     Reuters
    -0.65
    ned
    -0.64
     Kinnikuman
    -0.63
     Bronx
    -0.61
    Bloomberg
    -0.59
     Fallon
    -0.58
     thirds
    -0.57
     Bloomberg
    -0.57
    giving
    -0.55
    POSITIVE LOGITS
    oral
    1.27
    onics
    1.25
    ures
    1.19
    orial
    1.15
    ors
    1.09
    icut
    1.04
    ure
    1.04
    rix
    1.00
    icons
    0.99
    onica
    0.98
    Activations Density 0.039%

    No Known Activations