© 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. 8028
    Prev
    Next
    INDEX
    Explanations

    references to places and potential dangers present in the surroundings

    oai_token-act-pair · gpt-3.5-turbo

    references to safety concerns and hazards

    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
     Femin
    -0.94
     Promotion
    -0.86
     endorsement
    -0.84
     endorsements
    -0.82
     affirmative
    -0.82
    Tumblr
    -0.80
     feminism
    -0.79
     Relationship
    -0.76
    femin
    -0.76
     Partnership
    -0.76
    POSITIVE LOGITS
     stroll
    1.27
     trek
    1.27
     disembark
    1.24
     evacuated
    1.19
     perched
    1.17
     lug
    1.17
     evacuate
    1.16
     rapp
    1.15
     wander
    1.14
     slept
    1.12
    Activations Density 0.571%

    No Known Activations