Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 12451
    Prev
    Next
    INDEX
    Explanations

    the word "ban" or variations of it within the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ban" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Merit
    -0.79
    VERTISEMENT
    -0.78
    PRES
    -0.78
    EMS
    -0.70
    ITNESS
    -0.68
     mm
    -0.68
    FORMATION
    -0.68
     SERV
    -0.67
    Trend
    -0.66
    VIDEO
    -0.66
    POSITIVE LOGITS
    ban
    1.46
    anas
    1.09
    quet
    1.09
    igan
    1.02
    anan
    0.95
    ning
    0.93
    ner
    0.92
    igans
    0.91
    etsu
    0.90
    etooth
    0.90
    Activations Density 0.004%

    No Known Activations