© 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. 6-RES-JB
    11. 2668
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find mentions of top entities or superlatives in the context of the world or global scope

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "s" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lauder
    -0.72
    Å¡
    -0.68
    ¿½
    -0.66
    docker
    -0.64
     Slate
    -0.62
     Sale
    -0.62
    iov
    -0.60
    yz
    -0.60
    HOU
    -0.59
    bush
    -0.59
    POSITIVE LOGITS
    selves
    1.06
     tallest
    0.84
     premiere
    0.84
     foremost
    0.81
     Greatest
    0.78
     greatest
    0.77
    ifted
    0.77
     oldest
    0.75
    pecially
    0.75
    ankind
    0.74
    Activations Density 0.101%

    No Known Activations