Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 4084
    Prev
    Next
    INDEX
    Explanations

    words related to experiencing strong emotions or impacts

    oai_token-act-pair · gpt-3.5-turbo

    words related to emotional or mental states of being overwhelmed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ference
    -0.71
    humans
    -0.65
    bidden
    -0.64
    ities
    -0.64
    oulder
    -0.63
    xy
    -0.63
    ifications
    -0.62
    anamo
    -0.62
    rams
    -0.61
    itarian
    -0.59
    POSITIVE LOGITS
     reeling
    1.01
     conduc
    0.84
     reel
    0.83
    sembly
    0.81
    GGGGGGGG
    0.81
     earthqu
    0.79
    ©¶æ¥µ
    0.75
    ulz
    0.74
    OND
    0.74
    DIV
    0.73
    Activations Density 0.012%

    No Known Activations