© 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. 12179
    Prev
    Next
    INDEX
    Explanations

    references to the term "och" with varying levels of activation, possibly indicating a specific focus on documents including this term

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Moch" or variations of it

    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
    REC
    -0.62
     href
    -0.61
     permission
    -0.61
    ERC
    -0.60
     variance
    -0.59
     Wass
    -0.59
    Bird
    -0.59
    Madison
    -0.57
     Archangel
    -0.57
    GMT
    -0.57
    POSITIVE LOGITS
    rane
    1.21
    orus
    1.12
    lear
    1.03
    schild
    1.02
    ocolate
    0.98
    rome
    0.95
    owa
    0.94
    ocobo
    0.92
    och
    0.91
    inese
    0.90
    Activations Density 0.018%

    No Known Activations