© 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. 0-RES-JB
    11. 7666
    Prev
    Next
    INDEX
    Explanations

    words with the substring 'asp'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "asp"

    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
     meets
    -0.64
     Dun
    -0.63
     Town
    -0.63
     bug
    -0.62
     doubles
    -0.61
     lock
    -0.60
     Hay
    -0.59
     label
    -0.58
     hikes
    -0.58
     heading
    -0.58
    POSITIVE LOGITS
    asp
    4.64
    aspx
    1.64
    asc
    1.35
    aspberry
    1.30
    php
    1.23
    htm
    1.11
    asper
    1.10
    isp
    1.03
    aco
    1.03
    adr
    1.01
    Activations Density 0.017%

    No Known Activations