© 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. 10304
    Prev
    Next
    INDEX
    Explanations

    keywords related to consumables or consumable products

    oai_token-act-pair · gpt-3.5-turbo

    terms related to consumable products or resources

    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
     Shepherd
    -0.71
     Hollow
    -0.70
     Ferdinand
    -0.65
    riad
    -0.65
     Butterfly
    -0.62
     Refuge
    -0.62
    steen
    -0.62
     Bard
    -0.62
     Armory
    -0.61
     Palmer
    -0.60
    POSITIVE LOGITS
    ptions
    1.09
    ptive
    1.06
     consum
    1.02
    ables
    1.00
    ptives
    0.93
    ensible
    0.89
    itures
    0.88
    urable
    0.85
    Quantity
    0.84
    soDeliveryDate
    0.82
    Activations Density 0.006%

    No Known Activations