© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 7877
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "previously" or time-related references

    oai_token-act-pair · gpt-3.5-turbo

    references to time and temporal transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aby
    -0.71
    wake
    -0.69
    atur
    -0.68
    =>
    -0.67
    rench
    -0.67
    redo
    -0.66
    akens
    -0.65
    Rush
    -0.65
    Notice
    -0.65
    Rust
    -0.65
    POSITIVE LOGITS
     consisted
    0.78
     hadn
    0.77
     existed
    0.69
     relied
    0.68
    had
    0.67
     weren
    0.66
     wasn
    0.64
    didn
    0.64
     didn
    0.64
     tended
    0.64
    Activations Density 0.291%

    No Known Activations