© 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. 8-RES-JB
    11. 16887
    Prev
    Next
    INDEX
    Explanations

    phrases expressing importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    expressions emphasizing the significance or importance of various subjects

    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
    ãĥ³ãĤ¸
    -0.83
    ©¶æ
    -0.76
    ahime
    -0.76
    ARP
    -0.75
    rys
    -0.72
    guyen
    -0.71
    uthor
    -0.70
    apons
    -0.69
    viks
    -0.64
    uga
    -0.64
    POSITIVE LOGITS
    lessly
    0.86
    lessness
    0.85
     tremendously
    0.75
     enormously
    0.73
     chiefly
    0.69
     hugely
    0.67
    ingly
    0.66
    iest
    0.66
     greatly
    0.66
     aloud
    0.65
    Activations Density 0.035%

    No Known Activations