© 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. 23445
    Prev
    Next
    INDEX
    Explanations

    references to time periods, specifically the past year, and occasionally to shorter time frames

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, particularly years and decades

    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
     Saras
    -0.62
     Clause
    -0.60
     phr
    -0.60
     Hearts
    -0.60
     Fram
    -0.60
     breached
    -0.58
     breaching
    -0.58
    ogle
    -0.57
     sarc
    -0.56
     Selection
    -0.56
    POSITIVE LOGITS
    long
    0.85
    frames
    0.85
    teenth
    0.81
    mill
    0.75
    eteenth
    0.75
    orate
    0.74
    SPONSORED
    0.72
    fuck
    0.72
    share
    0.71
    Mill
    0.70
    Activations Density 0.080%

    No Known Activations