© 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. 11-RES-JB
    11. 2066
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "ind" in various contexts within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TI
    -0.66
     classified
    -0.65
    terday
    -0.65
     stren
    -0.57
     disbel
    -0.56
    PORT
    -0.56
     critically
    -0.56
     unsur
    -0.56
    iannopoulos
    -0.56
    ques
    -0.55
    POSITIVE LOGITS
    erella
    1.46
    ebted
    1.33
    icator
    1.26
    eer
    1.17
    icators
    1.15
    rome
    1.08
    ividually
    1.07
    orf
    1.07
    ication
    1.05
    icative
    1.02
    Activations Density 0.030%

    No Known Activations