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. 8941
    Prev
    Next
    INDEX
    Explanations

    words related to the term "Fre"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Freescale," referring to a technology or semiconductor company

    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
    anwhile
    -0.74
     Takeru
    -0.68
     fluor
    -0.68
     dissolved
    -0.66
    LESS
    -0.64
     Ancients
    -0.63
     Mori
    -0.63
     Izan
    -0.63
     Beir
    -0.62
    BuyableInstoreAndOnline
    -0.62
    POSITIVE LOGITS
    eport
    1.08
    natureconservancy
    1.03
    galitarian
    0.95
    eway
    0.94
    estone
    0.93
    ck
    0.93
    ighter
    0.92
    eman
    0.91
    cker
    0.91
    eland
    0.90
    Activations Density 0.009%

    No Known Activations