© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 22668
    Prev
    Next
    INDEX
    Explanations

    we are unable to determine the specific pattern this neuron is looking for as the activations do not provide a clear indication

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "we"

    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
     quo
    -0.77
    ional
    -0.62
     derail
    -0.62
     sucker
    -0.62
     LSD
    -0.61
    uate
    -0.61
     gratification
    -0.60
     Wol
    -0.59
     starvation
    -0.59
     pedoph
    -0.59
    POSITIVE LOGITS
    bsite
    1.38
    eping
    1.07
    aning
    1.06
    IRD
    1.05
    ighed
    1.01
    eks
    0.99
    arers
    0.98
    ird
    0.97
    akens
    0.96
    aving
    0.95
    Activations Density 0.097%

    No Known Activations