© 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. 3-RES-JB
    11. 10733
    Prev
    Next
    INDEX
    Explanations

    mentions of real estate properties, such as offices, retail centers, and residential buildings

    oai_token-act-pair · gpt-3.5-turbo

    specific types of commercial and residential property descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.83
     Krypt
    -0.75
     vain
    -0.75
     interrog
    -0.75
     maths
    -0.74
     plagiar
    -0.74
     physic
    -0.72
     paternity
    -0.71
     counterfe
    -0.71
     Guant
    -0.70
    POSITIVE LOGITS
     plaza
    0.93
    tyard
    0.86
    Square
    0.83
    thouse
    0.83
     Plaza
    0.81
    eria
    0.80
    Layout
    0.79
    unicip
    0.79
    plates
    0.78
    ominium
    0.78
    Activations Density 0.523%

    No Known Activations