© 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. 10-RES-JB
    11. 11382
    Prev
    Next
    INDEX
    Explanations

    mentions of locations associated with personal dwellings

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "home."

    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
    uel
    -0.70
    immers
    -0.69
    andum
    -0.68
    haps
    -0.63
    amen
    -0.61
    ãģĨ
    -0.61
    */(
    -0.60
     Samson
    -0.58
     sshd
    -0.58
    ussen
    -0.57
    POSITIVE LOGITS
    coming
    1.15
    opathic
    1.02
    pun
    1.01
    comings
    0.98
    opath
    0.93
    chool
    0.93
    opathy
    0.91
    pages
    0.89
     turf
    0.88
    grown
    0.85
    Activations Density 0.044%

    No Known Activations