© 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. 21785
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific products

    oai_token-act-pair · gpt-3.5-turbo

    terms related to agriculture, food products, and everyday objects

    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
    ãĥĥãĥī
    -0.85
    hower
    -0.83
    PDATE
    -0.74
     acknow
    -0.74
    odiac
    -0.70
    ãĤ¦ãĤ¹
    -0.69
    姫
    -0.66
    fml
    -0.65
    é¾įå¥ij士
    -0.65
    Reloaded
    -0.64
    POSITIVE LOGITS
     prototype
    0.66
    ancies
    0.66
     multiplication
    0.63
     rotation
    0.62
     prototypes
    0.62
     hybrids
    0.62
    hers
    0.60
     multic
    0.59
     pairs
    0.59
     contamin
    0.58
    Activations Density 0.544%

    No Known Activations