© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 5202
    Prev
    Next
    INDEX
    Explanations

    The neuron looks for pairs of words indicating a relationship or comparison

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to quantities or numerical details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mx
    -0.79
    bg
    -0.75
    Fra
    -0.75
    oots
    -0.72
    Anim
    -0.72
    emen
    -0.68
    nw
    -0.67
    agents
    -0.67
    Farm
    -0.67
    apps
    -0.67
    POSITIVE LOGITS
     ensuing
    1.41
     consequ
    1.34
     resultant
    1.31
     inability
    1.30
     willingness
    1.27
     likelihood
    1.20
     accompanying
    1.19
     propensity
    1.18
     possibility
    1.16
     impossibility
    1.15
    Activations Density 0.265%

    No Known Activations