© 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. 4-RES-JB
    11. 2208
    Prev
    Next
    INDEX
    Explanations

    words related to decomposition and dehydration

    oai_token-act-pair · gpt-3.5-turbo

    words related to decomposition processes and related scientific concepts

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

    No Comments

    Negative Logits
    reon
    -0.78
    Ãį
    -0.72
    CVE
    -0.72
    ror
    -0.71
    aj
    -0.70
    owitz
    -0.69
    follow
    -0.69
    Mand
    -0.66
    ihad
    -0.65
    orial
    -0.65
    POSITIVE LOGITS
     toilets
    0.81
     fluids
    0.77
    gradation
    0.77
     organisms
    0.74
     glands
    0.73
     ponds
    0.73
     pods
    0.72
     plastics
    0.71
     wast
    0.71
     embryos
    0.71
    Activations Density 0.111%

    No Known Activations