© 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. 23126
    Prev
    Next
    INDEX
    Explanations

    mentions of bloggers, particularly those with specific roles or actions related to their work

    oai_token-act-pair · gpt-3.5-turbo

    mentions of bloggers and their activities

    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
    IELD
    -0.84
    allic
    -0.70
     Pesh
    -0.70
    LS
    -0.69
    inho
    -0.65
     Medic
    -0.63
     Centers
    -0.62
     Medicine
    -0.61
     Oaks
    -0.61
    ZI
    -0.61
    POSITIVE LOGITS
     blogger
    1.17
     bloggers
    1.13
     blogging
    1.09
    blogs
    1.07
    osphere
    1.00
     blogs
    0.97
    irtual
    0.94
    blogspot
    0.92
    culosis
    0.86
     blog
    0.83
    Activations Density 0.008%

    No Known Activations