© 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. 0-RES-JB
    11. 534
    Prev
    Next
    INDEX
    Explanations

    phrases related to concentration or focus

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "concentrated" and its variations in the context of grouping or centralizing entities or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gate
    -0.70
    ESA
    -0.69
    SI
    -0.67
    friend
    -0.64
    suit
    -0.64
    bah
    -0.63
    Thom
    -0.63
     reviewer
    -0.62
    worthiness
    -0.62
     sue
    -0.61
    POSITIVE LOGITS
     concentrated
    3.68
     clustered
    1.69
     dispersed
    1.64
     focused
    1.47
     concentrating
    1.46
     concentration
    1.40
     Concent
    1.39
     concent
    1.34
     diluted
    1.31
     confined
    1.28
    Activations Density 0.019%

    No Known Activations