© 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. 11-RES-JB
    11. 17272
    Prev
    Next
    INDEX
    Explanations

    actions related to decision-making and relationship dynamics

    oai_token-act-pair · gpt-3.5-turbo

    actions and decisions made by women in various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peak
    -0.74
     Insight
    -0.68
    Magikarp
    -0.68
     Hits
    -0.66
     Hebdo
    -0.64
    âĺħ
    -0.63
    Bench
    -0.62
     Standing
    -0.62
     sqor
    -0.60
    Wiki
    -0.59
    POSITIVE LOGITS
     marry
    1.59
     divorce
    1.41
     divor
    1.26
     babys
    1.20
     divorced
    1.19
     contrace
    1.18
     conceive
    1.17
     married
    1.15
     groom
    1.08
     bury
    1.08
    Activations Density 0.443%

    No Known Activations