© 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. 1-RES-JB
    11. 9048
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named Kagan at different levels of significance

    oai_token-act-pair · gpt-3.5-turbo

    the name "Reagan" and its variations, indicating a focus on references to this individual

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mutual
    -0.73
     advers
    -0.70
    upon
    -0.69
     predictive
    -0.67
     probability
    -0.65
     backlog
    -0.65
     abdom
    -0.64
     apprehension
    -0.64
     likelihood
    -0.64
     fairness
    -0.63
    POSITIVE LOGITS
    agan
    1.20
    igans
    1.10
    atin
    0.98
    wald
    0.94
    stal
    0.93
    igan
    0.93
    itating
    0.92
    lein
    0.91
    emon
    0.90
    zeb
    0.90
    Activations Density 0.004%

    No Known Activations