© 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. 3-RES-JB
    11. 15172
    Prev
    Next
    INDEX
    Explanations

    words related to connections or associations between entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "connection" in relation to events or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ħ¢
    -0.77
     helicop
    -0.75
    orically
    -0.70
    otos
    -0.70
    avis
    -0.66
    osite
    -0.66
    oral
    -0.66
    oby
    -0.65
    corn
    -0.65
    issan
    -0.61
    POSITIVE LOGITS
     connection
    1.05
     connections
    0.96
    ioned
    0.92
    ability
    0.88
    connection
    0.85
    abilities
    0.80
     links
    0.80
     ties
    0.80
    connected
    0.78
     link
    0.78
    Activations Density 0.024%

    No Known Activations