© 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. 21879
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific type of popular online game series

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific gaming console or brand

    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
    advertisement
    -0.66
    sheets
    -0.60
    glers
    -0.59
    writers
    -0.59
     Myster
    -0.57
     Territories
    -0.56
     datas
    -0.56
     Rhod
    -0.55
     Flavoring
    -0.55
     Malays
    -0.54
    POSITIVE LOGITS
    lehem
    0.86
    assador
    0.84
    ixture
    0.79
    pas
    0.77
    ibo
    0.77
    ICAN
    0.77
    achusetts
    0.76
    ments
    0.74
    akeru
    0.74
    ocent
    0.72
    Activations Density 0.080%

    No Known Activations