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. 10506
    Prev
    Next
    INDEX
    Explanations

    words related to the importance or significance of a role in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the significance or importance of a role in various contexts

    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
     roomm
    -0.69
    azes
    -0.67
    fts
    -0.65
     fists
    -0.64
     peas
    -0.62
     traps
    -0.60
     limbs
    -0.59
    anders
    -0.59
     butterflies
    -0.59
    arus
    -0.58
    POSITIVE LOGITS
    âĹ¼
    0.77
     Advertisement
    0.72
     role
    0.71
    lycer
    0.65
     analogous
    0.64
     GOODMAN
    0.63
    WARD
    0.63
     Model
    0.63
    olin
    0.63
    rophe
    0.62
    Activations Density 0.080%

    No Known Activations