© 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. 8621
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events or achievements

    oai_token-act-pair · gpt-3.5-turbo

    historical references to significant events and amendments

    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
    li
    -0.69
     interrupts
    -0.68
    assy
    -0.66
    ggles
    -0.66
    etermin
    -0.64
    ati
    -0.64
    atical
    -0.62
    interstitial
    -0.62
    ylon
    -0.62
    hig
    -0.61
    POSITIVE LOGITS
     deserved
    1.05
    didn
    1.00
     didn
    0.99
     benefited
    0.99
     regretted
    0.99
     repaid
    0.97
     succeeded
    0.96
     knew
    0.95
    failed
    0.95
    Had
    0.93
    Activations Density 1.190%

    No Known Activations