© 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. 8676
    Prev
    Next
    INDEX
    Explanations

    phrases related to improvement and progress

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to cooperation and support 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
    retty
    -0.61
    fetched
    -0.60
     skipped
    -0.59
    uncle
    -0.58
    assium
    -0.57
     ado
    -0.57
     anyway
    -0.57
    akespe
    -0.57
     tabl
    -0.55
    bare
    -0.55
    POSITIVE LOGITS
     sustainable
    0.87
     collaborative
    0.77
     sustainability
    0.75
     Sustainable
    0.75
     workforce
    0.72
    ustain
    0.68
     diverse
    0.67
     innovative
    0.66
     productivity
    0.65
    cellence
    0.65
    Activations Density 1.121%

    No Known Activations