© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 19966
    Prev
    Next
    INDEX
    Explanations

    websites ending in '.com'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the domain "com" related to websites or online content

    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
     cub
    -0.67
     Balt
    -0.67
     Lump
    -0.63
    ĪĴ
    -0.62
     sher
    -0.61
     unic
    -0.60
     USDA
    -0.60
     AFL
    -0.58
     retali
    -0.58
    ĺħ
    -0.58
    POSITIVE LOGITS
    pleted
    1.13
    fortable
    1.08
    pletion
    1.01
    pleting
    0.98
    puters
    0.96
    ittee
    0.94
    ité
    0.92
    ptroller
    0.92
    fman
    0.91
    anooga
    0.91
    Activations Density 0.031%

    No Known Activations