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. 12500
    Prev
    Next
    INDEX
    Explanations

    strong negative emotions or ominous events

    oai_token-act-pair · gpt-3.5-turbo

    expressions of fear or anxiety

    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
    utra
    -0.73
    ECD
    -0.72
    cius
    -0.69
    elman
    -0.68
    ONSORED
    -0.67
    zanne
    -0.67
    Priv
    -0.67
    zu
    -0.65
    Lib
    -0.64
    ropri
    -0.64
    POSITIVE LOGITS
    locks
    1.20
    icum
    0.93
    locked
    0.91
     dread
    0.89
    etheless
    0.87
     Dread
    0.76
    nant
    0.74
     cumbers
    0.74
     wig
    0.72
    nuts
    0.68
    Activations Density 0.027%

    No Known Activations