© 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. 20445
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically related to a company or brand

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Bodega," likely in relation to food or cultural context

    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
    soDeliveryDate
    -0.88
    hips
    -0.79
     "$:/
    -0.76
     Dragonbound
    -0.75
    rike
    -0.74
    quished
    -0.70
    idav
    -0.66
    ees
    -0.64
    indu
    -0.64
     Express
    -0.64
    POSITIVE LOGITS
    grad
    1.07
    gradation
    1.06
    grading
    0.99
    velop
    0.98
    lete
    0.91
    ga
    0.91
    grades
    0.86
    vous
    0.86
    BUG
    0.86
    jing
    0.85
    Activations Density 0.040%

    No Known Activations