© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 17814
    Prev
    Next
    INDEX
    Explanations

    adjectives or phrases indicating something that is limitless, inexhaustible, or unavoidable

    oai_token-act-pair · gpt-3.5-turbo

    terms related to necessity and abundance

    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
     albums
    -0.71
    Reviewer
    -0.68
     album
    -0.65
     Rover
    -0.65
     loader
    -0.64
     Freeze
    -0.64
     immersion
    -0.63
     Devil
    -0.63
     umbrella
    -0.61
     objectives
    -0.61
    POSITIVE LOGITS
    structed
    1.24
    cious
    1.11
    vention
    1.09
    hibited
    1.08
    aturally
    1.07
    cipl
    1.02
    jured
    1.00
    cus
    0.99
    ptive
    0.98
    perate
    0.96
    Activations Density 0.059%

    No Known Activations