© 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. 12898
    Prev
    Next
    INDEX
    Explanations

    references to specific smartphone models, particularly those from Samsung like the Galaxy S5 and S6

    oai_token-act-pair · gpt-3.5-turbo

    references to specific smartphone models and their features

    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
    opathic
    -0.89
     contagious
    -0.76
    imens
    -0.75
    msg
    -0.69
    glers
    -0.69
    ulously
    -0.68
    staff
    -0.66
    reek
    -0.65
     âĸĪ
    -0.65
    eston
    -0.64
    POSITIVE LOGITS
     Anniversary
    0.88
    ĺħ
    0.77
     chipset
    0.74
     motherboard
    0.74
     Gaming
    0.73
     GHz
    0.69
    andro
    0.68
     successors
    0.68
    Ħ¢
    0.68
     owners
    0.68
    Activations Density 0.094%

    No Known Activations