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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8351
    Prev
    Next
    INDEX
    Explanations

    specific last names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Carr" or terms related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĨĴ
    -0.86
    ku
    -0.77
     Pixie
    -0.74
    lasses
    -0.68
    utral
    -0.67
    £ı
    -0.66
    dayName
    -0.66
    ¥µ
    -0.64
    xual
    -0.62
    zza
    -0.61
    POSITIVE LOGITS
    agher
    1.06
    abilia
    0.91
    agh
    0.91
    anging
    0.89
    anged
    0.89
    issa
    0.89
    INGTON
    0.89
    andom
    0.87
    ange
    0.85
    abeth
    0.85
    Activations Density 0.015%

    No Known Activations