© 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. 4-RES-JB
    11. 6055
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Mexico or its citizens

    oai_token-act-pair · gpt-3.5-turbo

    terms related to Mexican culture and societal concepts

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

    No Comments

    Negative Logits
     pity
    -0.66
     Bakr
    -0.63
     Feast
    -0.62
     breath
    -0.61
     indictment
    -0.59
     fabrication
    -0.57
    avorite
    -0.57
     Origin
    -0.56
     resemblance
    -0.55
     Hollow
    -0.55
    POSITIVE LOGITS
    icator
    1.30
    ic
    1.22
    icity
    1.22
    ique
    1.19
    icals
    1.19
    iation
    1.17
    icates
    1.16
    ication
    1.16
    ications
    1.16
    icators
    1.16
    Activations Density 0.041%

    No Known Activations