© 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. 11457
    Prev
    Next
    INDEX
    Explanations

    words related to the term "city."

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the substring "iti" in various contexts

    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
     axes
    -0.73
     dislike
    -0.69
     macros
    -0.67
     Nazis
    -0.62
     Rust
    -0.61
     conviction
    -0.60
     crate
    -0.58
     own
    -0.58
     takedown
    -0.58
     hatred
    -0.57
    POSITIVE LOGITS
    iti
    4.57
    ati
    1.16
    itaire
    1.11
    ici
    1.09
     Initi
    1.09
    oti
    1.08
    ito
    1.06
    strument
    1.04
    iqu
    1.02
    itus
    1.02
    Activations Density 0.005%

    No Known Activations