© 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. 3265
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences related to actions being done

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to," indicating a focus on infinitive verbs or actions

    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
     deductions
    -0.68
     deviations
    -0.61
     detached
    -0.60
     ranges
    -0.60
     transformations
    -0.60
     knots
    -0.60
     binaries
    -0.59
     crossings
    -0.59
     activated
    -0.58
     surgeon
    -0.58
    POSITIVE LOGITS
     coincide
    1.43
     commemorate
    1.42
     celebrate
    1.31
    pless
    1.22
     promote
    1.06
     accompany
    1.05
     emphasize
    1.03
     remind
    0.97
    wered
    0.96
     illustrate
    0.96
    Activations Density 0.240%

    No Known Activations