© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    6. 17647
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find specific dates in the format of month names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "ember" and its variants, indicating a focus on the month of December

    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
    SPONSORED
    -0.75
     Strauss
    -0.74
     Collider
    -0.69
     Kissinger
    -0.65
    egal
    -0.64
     Wonderful
    -0.63
    overs
    -0.62
     Medicare
    -0.59
    omen
    -0.59
     Pathfinder
    -0.58
    POSITIVE LOGITS
    mented
    0.98
    mentation
    0.93
    ember
    0.93
    getic
    0.92
    gence
    0.92
    gdala
    0.91
    gments
    0.90
    nesday
    0.89
    ment
    0.86
    utive
    0.84
    Activations Density 0.009%

    No Known Activations