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. 11-RES-JB
    6. 622
    Prev
    Next
    INDEX
    Explanations

    words related to the distribution of resources or wealth

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of distribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gery
    -0.75
    --+
    -0.72
    glers
    -0.71
     ABE
    -0.68
    gged
    -0.64
    ton
    -0.63
    TAG
    -0.63
    mentation
    -0.63
     Huss
    -0.62
    abee
    -0.62
    POSITIVE LOGITS
     ledger
    1.09
    al
    0.92
     distribute
    0.89
     Distribution
    0.84
    ally
    0.81
    女
    0.81
     distribution
    0.80
    aler
    0.80
    itarian
    0.78
    sheets
    0.76
    Activations Density 0.077%

    No Known Activations