© 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. 7009
    Prev
    Next
    INDEX
    Explanations

    terms related to academic research, demographics, and medical characteristics

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to ethnicity and social behavior in the context of war and strategy

    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
    wered
    -0.85
     pus
    -0.75
     Grail
    -0.72
    eday
    -0.72
    pired
    -0.70
    Company
    -0.67
    Brave
    -0.66
    stros
    -0.65
     unheard
    -0.62
    Bomb
    -0.62
    POSITIVE LOGITS
     heterogeneity
    1.27
     attitudes
    1.20
     biases
    1.19
     preferences
    1.16
     variables
    1.13
     characteristics
    1.13
     influences
    1.12
     reperto
    1.12
     propensity
    1.11
     perceptions
    1.11
    Activations Density 0.400%

    No Known Activations