© 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. 7057
    Prev
    Next
    INDEX
    Explanations

    words related to urban planning, infrastructure, and construction

    oai_token-act-pair · gpt-3.5-turbo

    the suffix "est" which typically indicates the superlative form of adjectives

    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
    shock
    -0.70
    perty
    -0.67
    senal
    -0.63
    veyard
    -0.62
    sterdam
    -0.61
    teenth
    -0.61
    ppo
    -0.60
    gee
    -0.60
    clusive
    -0.59
     calming
    -0.59
    POSITIVE LOGITS
    imates
    1.04
    ruct
    1.03
    reet
    1.02
    ream
    1.00
    imating
    0.99
    alker
    0.96
    oppers
    0.93
    imate
    0.90
    iary
    0.90
    imation
    0.89
    Activations Density 0.033%

    No Known Activations