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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 20052
    Prev
    Next
    INDEX
    Explanations

    terms related to technology units or brands

    oai_token-act-pair · gpt-3.5-turbo

    references to gigabyte-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mayo
    -0.71
    OPLE
    -0.70
     CONTROL
    -0.68
     LIFE
    -0.66
    CLASSIFIED
    -0.66
     Continued
    -0.65
    byter
    -0.63
    xual
    -0.63
     Medline
    -0.62
    tsky
    -0.61
    POSITIVE LOGITS
    abyte
    1.24
     Gig
    1.14
    hetto
    1.14
    abytes
    1.06
    amera
    1.03
    apixel
    0.96
    oliath
    0.96
    agos
    0.94
    galitarian
    0.91
    ertodd
    0.90
    Activations Density 0.008%

    No Known Activations