Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 17220
    Prev
    Next
    INDEX
    Explanations

    words related to education and academia, particularly focusing on students and campuses

    oai_token-act-pair · gpt-3.5-turbo

    significant nouns related to individuals, organizations, and events

    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
    }.
    -0.71
    ?".
    -0.65
    ''.
    -0.65
    ]."
    -0.64
    )?
    -0.62
    "}
    -0.60
    ?).
    -0.60
    Merit
    -0.56
    )."
    -0.56
     alike
    -0.54
    POSITIVE LOGITS
    obook
    0.57
    escription
    0.56
    eanor
    0.55
    argon
    0.55
     hotline
    0.55
    wikipedia
    0.53
    oqu
    0.52
    anche
    0.51
    uese
    0.51
    wagon
    0.50
    Activations Density 1.521%

    No Known Activations