© 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. 2-RES-JB
    11. 1584
    Prev
    Next
    INDEX
    Explanations

    mentions of 'syn' in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    references to synonyms or related terminology in language or music

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORED
    -0.93
    aneers
    -0.88
    200000
    -0.75
    Merit
    -0.74
    IVE
    -0.71
    ardless
    -0.70
     429
    -0.67
    doms
    -0.67
     Ancients
    -0.67
    INA
    -0.67
    POSITIVE LOGITS
     syn
    1.29
    agog
    1.17
    agogue
    1.06
     sync
    0.99
    apse
    0.99
    apses
    0.95
    emy
    0.86
     Syn
    0.83
    opsis
    0.81
    esthetic
    0.80
    Activations Density 0.005%

    No Known Activations