© 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. 8-RES-JB
    11. 4554
    Prev
    Next
    INDEX
    Explanations

    verb phrases related to physical actions and processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to water and environmental effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     retrospective
    -0.70
    javascript
    -0.68
    lando
    -0.68
     invite
    -0.67
     homepage
    -0.67
     Fn
    -0.67
    yrinth
    -0.66
     itiner
    -0.66
    icester
    -0.65
     invitation
    -0.65
    POSITIVE LOGITS
     oxid
    1.18
    oxide
    1.09
     melted
    1.09
     electroly
    1.07
     veins
    1.03
     poured
    1.03
     chlorine
    1.03
     soluble
    1.02
     pumped
    1.02
     additives
    1.00
    Activations Density 0.767%

    No Known Activations