© 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. 2-RES-JB
    11. 3882
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to the word "ming" or similar endings

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles related to various forms of activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izons
    -0.71
    ibaba
    -0.65
     EE
    -0.63
    MpServer
    -0.63
    eva
    -0.61
    berus
    -0.61
    effic
    -0.59
     inches
    -0.59
     telev
    -0.58
    天
    -0.58
    POSITIVE LOGITS
    ming
    1.08
    bird
    1.07
    ication
    0.93
    mers
    0.93
    olin
    0.88
    ening
    0.86
    eer
    0.84
    bing
    0.84
    tons
    0.83
    birds
    0.83
    Activations Density 0.019%

    No Known Activations