Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4329
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific cultural or regional references

    oai_token-act-pair · gpt-3.5-turbo

    words related to the French language and its dialects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bott
    -0.75
     RELEASE
    -0.74
    Doug
    -0.72
     Clapper
    -0.72
     Bung
    -0.71
     Geoff
    -0.70
    /-
    -0.70
    cliffe
    -0.70
     Hig
    -0.69
     Pip
    -0.69
    POSITIVE LOGITS
    ia
    1.20
    ian
    1.14
    ians
    1.10
    iosis
    1.03
    idian
    1.01
    ese
    1.00
    iac
    0.97
    ium
    0.95
    iah
    0.94
    ien
    0.92
    Activations Density 0.216%

    No Known Activations