© 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. 0-RES-JB
    11. 20363
    Prev
    Next
    INDEX
    Explanations

    words related to the city of Melbourne

    oai_token-act-pair · gpt-3.5-turbo

    names and terms associated with specific locations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pul
    -0.65
    ãĥ¥
    -0.65
    iced
    -0.64
    OUGH
    -0.63
     affidav
    -0.63
     intric
    -0.62
    irst
    -0.62
     epid
    -0.59
     nar
    -0.59
     laure
    -0.58
    POSITIVE LOGITS
    bourne
    3.43
    brate
    2.95
    brates
    2.91
    borgh
    1.26
    bral
    1.23
    bourg
    1.20
    ppelin
    1.14
    gow
    1.05
    mania
    1.01
    INGTON
    1.00
    Activations Density 0.047%

    No Known Activations