© 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. 4-RES-JB
    11. 14410
    Prev
    Next
    INDEX
    Explanations

    phrases indicating similarities or comparisons

    oai_token-act-pair · gpt-3.5-turbo

    comparisons emphasizing similarity across various contexts

    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
     caches
    -0.66
     TAG
    -0.66
     pal
    -0.66
     helicop
    -0.63
     LIM
    -0.63
     overrun
    -0.62
     outwe
    -0.60
     extras
    -0.60
     maj
    -0.59
     premie
    -0.59
    POSITIVE LOGITS
    ²¾
    0.84
    same
    0.81
     Tradable
    0.79
    hov
    0.79
    ablishment
    0.78
     Berm
    0.78
    ovie
    0.77
    ^^^^
    0.77
    Ö¼
    0.76
    ":"/
    0.74
    Activations Density 0.290%

    No Known Activations