© 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. 7-RES-JB
    11. 17112
    Prev
    Next
    INDEX
    Explanations

    phrases related to possession or association

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or categories in various contexts

    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
    urus
    -0.82
    FontSize
    -0.68
    uart
    -0.66
    cius
    -0.65
    aph
    -0.65
    reporting
    -0.62
     Clouds
    -0.61
    fty
    -0.60
    umbnails
    -0.60
    iries
    -0.60
    POSITIVE LOGITS
     belongs
    0.81
     ours
    0.77
     represents
    0.73
     initiative
    0.71
     endeavor
    0.66
    ATURE
    0.66
    OULD
    0.65
     extends
    0.64
     phenomenon
    0.62
     shenan
    0.61
    Activations Density 0.484%

    No Known Activations