Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 19446
    Prev
    Next
    INDEX
    Explanations

    terms related to solid-state drives (SSDs)

    oai_token-act-pair · gpt-3.5-turbo

    terms related to solid-state drives (SSDs) and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mu
    -0.85
    bidden
    -0.83
     Kok
    -0.78
    roma
    -0.74
    jab
    -0.74
     Illusion
    -0.74
     Bam
    -0.73
    ilateral
    -0.72
     Vienna
    -0.72
     Mim
    -0.71
    POSITIVE LOGITS
     SSD
    3.09
     LCS
    1.99
    WD
    1.92
     HDD
    1.81
     WD
    1.45
     SATA
    1.43
    LCS
    1.42
     OPS
    1.33
     RAID
    1.30
     DDR
    1.20
    Activations Density 0.036%

    No Known Activations