© 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. 8-RES-JB
    11. 17588
    Prev
    Next
    INDEX
    Explanations

    descriptions of having all the necessary elements or features required for a specific task or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing completeness or totality regarding various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ende
    -0.68
    taboola
    -0.59
     IPS
    -0.58
    ahime
    -0.57
    MQ
    -0.57
     Merge
    -0.56
     endeavor
    -0.56
    ²¾
    -0.55
     gif
    -0.55
     Accessed
    -0.55
    POSITIVE LOGITS
     advantages
    0.96
     characteristics
    0.88
    same
    0.86
    forts
    0.83
     requisite
    0.80
     bells
    0.77
    burgh
    0.75
     amenities
    0.75
     qualities
    0.75
     privileges
    0.74
    Activations Density 0.202%

    No Known Activations