© 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. 3-RES-JB
    11. 2844
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the name "Muhammad"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Mohammad" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     steroids
    -0.72
     stakes
    -0.69
     resemb
    -0.68
     masks
    -0.68
     kinderg
    -0.65
     corners
    -0.64
     edges
    -0.63
     occupants
    -0.62
     mischief
    -0.61
     takeaway
    -0.61
    POSITIVE LOGITS
    nesty
    1.34
    endment
    1.31
    ilies
    1.18
    sterdam
    1.16
    essage
    1.13
    bitious
    1.09
    urai
    1.05
    ulet
    1.05
    borgh
    1.05
    azing
    1.03
    Activations Density 0.023%

    No Known Activations