© 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. 6953
    Prev
    Next
    INDEX
    Explanations

    specific phrases connected to detailed discussions or analysis

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, particularly "and," in various contexts throughout the text

    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
    DragonMagazine
    -0.76
    onia
    -0.71
    IRE
    -0.69
    ummer
    -0.67
    adra
    -0.67
    ega
    -0.67
    ãĥĨãĤ£
    -0.66
    \-
    -0.66
    Fif
    -0.64
    ãĤĵ
    -0.64
    POSITIVE LOGITS
     compares
    1.12
     how
    1.09
     discusses
    1.05
     concludes
    0.99
     adjusts
    0.98
     compare
    0.92
     pitfalls
    0.92
     examines
    0.91
     reveals
    0.91
     topics
    0.88
    Activations Density 0.353%

    No Known Activations