© 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. 17610
    Prev
    Next
    INDEX
    Explanations

    the preposition 'in' used to indicate a specific position or location

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "in" indicating context or location

    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
    Published
    -0.74
    incial
    -0.74
    âĿ
    -0.63
    ailability
    -0.62
    uterte
    -0.62
    bilt
    -0.59
    vice
    -0.59
    aptic
    -0.59
    estyles
    -0.58
    sworth
    -0.57
    POSITIVE LOGITS
    animate
    0.96
    lihood
    0.94
    organic
    0.86
    clus
    0.86
    liest
    0.84
    lier
    0.83
    ducers
    0.82
    clusively
    0.77
    authent
    0.76
     lieu
    0.74
    Activations Density 0.047%

    No Known Activations