© 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. 8-RES-JB
    11. 6147
    Prev
    Next
    INDEX
    Explanations

    mentions of locations being someone's home

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "home" in various contexts

    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
    sha
    -0.67
    uku
    -0.66
     haircut
    -0.61
     stride
    -0.59
     bite
    -0.57
    entle
    -0.57
     perspective
    -0.55
    asm
    -0.55
     Stephenson
    -0.54
    ussian
    -0.54
    POSITIVE LOGITS
    coming
    0.91
    quartered
    0.84
    liest
    0.83
    brew
    0.81
    chool
    0.79
    grown
    0.79
    opathy
    0.78
    lier
    0.78
    imately
    0.77
    oided
    0.75
    Activations Density 0.040%

    No Known Activations