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. 2194
    Prev
    Next
    INDEX
    Explanations

    words related to decrees or orders being issued

    oai_token-act-pair · gpt-3.5-turbo

    words relating to decrees and movements, particularly in a political or corporate context

    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
    missive
    -0.66
     translator
    -0.66
    ministic
    -0.65
     Vers
    -0.64
    peria
    -0.63
     Aval
    -0.62
    gers
    -0.62
    light
    -0.60
     sentiments
    -0.58
     Polo
    -0.58
    POSITIVE LOGITS
    ements
    1.05
    ooks
    0.88
    ety
    0.85
    ement
    0.84
    ards
    0.83
    ments
    0.82
    age
    0.82
    ework
    0.81
    oner
    0.81
    iard
    0.81
    Activations Density 0.052%

    No Known Activations