© 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. 0-RES-JB
    11. 22692
    Prev
    Next
    INDEX
    Explanations

    phrases related to connections or associations between entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "relation" or connections between entities or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rax
    -0.62
     blasted
    -0.61
    sav
    -0.60
    EEE
    -0.58
     Crazy
    -0.58
    casters
    -0.58
    Iv
    -0.58
     showcased
    -0.57
    Į
    -0.57
    busters
    -0.57
    POSITIVE LOGITS
     relation
    3.87
     relationship
    1.92
     relations
    1.76
     connection
    1.72
    relations
    1.57
     Relationship
    1.52
    relation
    1.50
     regards
    1.43
     resemblance
    1.41
     relationships
    1.40
    Activations Density 0.012%

    No Known Activations