© 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. 8-RES-JB
    11. 7026
    Prev
    Next
    INDEX
    Explanations

    phrases related to being a significant contributing factor to something happening or being present

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant contributions or factors in a situation

    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
    ]}
    -0.58
     Unsure
    -0.57
     mess
    -0.54
     sung
    -0.52
     dab
    -0.52
    ,...
    -0.52
     weap
    -0.51
    OTH
    -0.50
     %%
    -0.50
     lett
    -0.50
    POSITIVE LOGITS
    ordinate
    1.15
    humane
    1.14
    clus
    1.14
    efficiency
    1.10
    effic
    1.07
    versely
    1.06
    authent
    1.06
    effect
    1.05
    animate
    1.05
     essence
    1.04
    Activations Density 0.235%

    No Known Activations