© 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. 1293
    Prev
    Next
    INDEX
    Explanations

    comparisons using the word "as"

    oai_token-act-pair · gpt-3.5-turbo

    comparisons or similes that use the phrase "as [adjective] as."

    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
     respir
    -0.61
    Fs
    -0.60
    bryce
    -0.60
    çķ
    -0.59
     Picks
    -0.59
    lections
    -0.58
     Errors
    -0.58
    Firstly
    -0.57
    elsen
    -0.57
     Consolid
    -0.56
    POSITIVE LOGITS
    pired
    1.27
    pires
    1.08
    imilar
    0.99
    ym
    0.97
    ynchron
    0.93
    phalt
    0.93
     follows
    0.93
    phy
    0.92
     far
    0.89
    ocial
    0.86
    Activations Density 0.100%

    No Known Activations