© 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. 1-RES-JB
    11. 713
    Prev
    Next
    INDEX
    Explanations

    mentions of mobile applications, particularly the Apple App Store

    oai_token-act-pair · gpt-3.5-turbo

    references to applications and app stores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -1.02
    κ
    -0.73
    EStreamFrame
    -0.73
    ãĤ¬
    -0.69
    warts
    -0.69
    xual
    -0.69
     Holiday
    -0.65
     Karl
    -0.64
    ãģį
    -0.63
     Shakespeare
    -0.63
    POSITIVE LOGITS
    ointment
    1.24
    alach
    1.24
    rentices
    1.18
    arent
    1.15
    earances
    1.15
    ointed
    1.13
    reciation
    1.12
    arel
    1.09
    earance
    1.09
    rehens
    1.08
    Activations Density 0.012%

    No Known Activations