© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 16400
    Prev
    Next
    INDEX
    Explanations

    references to entering, breaking into, or being inside a specific physical location, like a home

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or residence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.74
    ussian
    -0.73
    velength
    -0.68
    rencies
    -0.67
    oneliness
    -0.66
     globalization
    -0.65
    andum
    -0.65
    auts
    -0.65
     datas
    -0.65
    ioxide
    -0.64
    POSITIVE LOGITS
    owner
    0.86
    tyard
    0.83
    chool
    0.82
     intruder
    0.81
     adjoining
    0.79
    wife
    0.79
     located
    0.77
     belonging
    0.76
     occupant
    0.76
    stead
    0.75
    Activations Density 0.107%

    No Known Activations