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. 24066
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or existence of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or existence of something

    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
    aign
    -0.78
    anish
    -0.72
    cham
    -0.71
    >>\
    -0.68
    isoft
    -0.67
    vernight
    -0.67
    angled
    -0.65
    rounded
    -0.65
    multipl
    -0.64
    aten
    -0.64
    POSITIVE LOGITS
     occasional
    0.91
     occasionally
    0.79
     anecd
    0.78
     plenty
    0.74
     some
    0.74
     somewhat
    0.70
     intermedi
    0.70
    rists
    0.68
     advoc
    0.67
     outl
    0.66
    Activations Density 0.138%

    No Known Activations