© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 20333
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing something to someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate provision or supply of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MQ
    -0.72
    idity
    -0.66
    AU
    -0.64
    BR
    -0.63
    wake
    -0.63
    kind
    -0.62
    TD
    -0.61
    leaf
    -0.60
    leave
    -0.59
    DF
    -0.59
    POSITIVE LOGITS
     ample
    1.01
     plenty
    0.96
     sufficient
    0.94
     priceless
    0.94
     limitless
    0.92
     innumerable
    0.92
     tons
    0.88
     unlimited
    0.87
     invaluable
    0.86
     countless
    0.86
    Activations Density 0.115%

    No Known Activations