Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 4046
    Prev
    Next
    INDEX
    Explanations

    Well, this neuron seems to be looking for specific numerical values, especially those related to financial figures

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and measurements

    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
    hol
    -0.79
    board
    -0.75
    aways
    -0.75
    fund
    -0.68
    cycl
    -0.67
    agan
    -0.66
    anol
    -0.66
    estone
    -0.64
    away
    -0.61
    boards
    -0.61
    POSITIVE LOGITS
    454
    1.09
    651
    1.09
    354
    1.09
    647
    1.07
    994
    1.06
    461
    1.05
    646
    1.05
    393
    1.05
    669
    1.05
    452
    1.04
    Activations Density 0.049%

    No Known Activations