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. 7-RES-JB
    6. 2350
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing resources and making recommendations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to recommendations or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inis
    -0.70
    .).
    -0.68
    =#
    -0.61
    anooga
    -0.61
    amon
    -0.61
    ].
    -0.59
    )!
    -0.58
    .#
    -0.58
    erd
    -0.58
    }.
    -0.57
    POSITIVE LOGITS
     Defendants
    0.59
     existing
    0.58
     perce
    0.57
     Defendant
    0.56
     finite
    0.56
     SCP
    0.55
     Plaintiff
    0.48
     perceptual
    0.48
     ASIC
    0.48
     invari
    0.47
    Activations Density 2.179%

    No Known Activations