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. 4-RES-JB
    6. 20738
    Prev
    Next
    INDEX
    Explanations

    medical conditions and terms related to technology and politics

    oai_token-act-pair · gpt-3.5-turbo

    nouns and proper nouns associated with brands and products

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

    No Comments

    Negative Logits
     ..."
    -0.81
    >]
    -0.60
     ....
    -0.55
    }.
    -0.53
     anymore
    -0.53
     shoulder
    -0.52
    ãģ¾
    -0.51
     ],
    -0.51
     haha
    -0.51
     dividing
    -0.51
    POSITIVE LOGITS
    ensibly
    0.76
    anyahu
    0.70
    hester
    0.70
    ashtra
    0.68
    ulhu
    0.64
    raltar
    0.63
    udos
    0.62
    iasis
    0.62
    unia
    0.61
    roma
    0.61
    Activations Density 0.503%

    No Known Activations