© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 11845
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning the concept of an online profile, often accompanied by actions or descriptions related to its management or content

    oai_token-act-pair · gpt-3.5-turbo

    mentions of user profiles, particularly in the context of social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actic
    -0.75
    nuts
    -0.72
    hers
    -0.72
     relent
    -0.67
    shall
    -0.67
    ners
    -0.66
    cible
    -0.64
    atorial
    -0.64
    agan
    -0.63
    iHUD
    -0.63
    POSITIVE LOGITS
     profile
    1.06
     profiles
    1.00
    ocl
    0.83
    Profile
    0.77
    onym
    0.76
     picture
    0.75
    ographies
    0.72
     Profile
    0.69
     template
    0.69
     Detail
    0.68
    Activations Density 0.027%

    No Known Activations