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. 20011
    Prev
    Next
    INDEX
    Explanations

    instances of the word "instill" and its variations

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "install" and related terms implying installation or introduction

    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
    neau
    -0.82
    udeau
    -0.79
    ixel
    -0.74
    opoulos
    -0.71
    icro
    -0.67
     Kro
    -0.66
    ouch
    -0.63
    iddled
    -0.63
     athlet
    -0.62
    ibble
    -0.62
    POSITIVE LOGITS
     anew
    0.80
     hatred
    0.74
    spir
    0.70
    Ire
    0.66
     memories
    0.64
    BALL
    0.64
     humility
    0.64
    FORMATION
    0.63
     havoc
    0.62
     Divinity
    0.62
    Activations Density 0.110%

    No Known Activations