© 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. 1-RES-JB
    11. 16452
    Prev
    Next
    INDEX
    Explanations

    words or terms related to neural activity and synapses

    oai_token-act-pair · gpt-3.5-turbo

    references to synapses and related terms in neuroscience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aneers
    -0.90
    ORED
    -0.85
    200000
    -0.83
    Rod
    -0.72
    ATER
    -0.72
    irin
    -0.70
    Merit
    -0.69
    ij士
    -0.69
    411
    -0.67
    Owner
    -0.67
    POSITIVE LOGITS
     syn
    1.41
    agog
    1.13
     sync
    0.98
    agogue
    0.97
     Syn
    0.89
    apse
    0.88
    apses
    0.83
     mosqu
    0.80
     synchronization
    0.77
    Syn
    0.74
    Activations Density 0.004%

    No Known Activations