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. 12058
    Prev
    Next
    INDEX
    Explanations

    references to furniture, particularly items found next to a bed

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to endings and concluding moments

    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
    anson
    -0.94
    alg
    -0.87
    ickr
    -0.77
    educ
    -0.75
    abase
    -0.74
    Reviewer
    -0.74
    char
    -0.72
    Asset
    -0.72
    OY
    -0.72
    irlf
    -0.72
    POSITIVE LOGITS
     ceremony
    0.70
     attendants
    0.66
     anniversary
    0.66
     devastation
    0.64
     misery
    0.63
     festivities
    0.62
     reception
    0.62
     fences
    0.61
     celebration
    0.60
     truce
    0.60
    Activations Density 0.176%

    No Known Activations