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. 7948
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a central theme or main point being discussed

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a conclusion or summarization

    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
    digy
    -0.82
    #$
    -0.76
    rouse
    -0.70
     Machina
    -0.69
    ulton
    -0.67
    xtap
    -0.67
    inen
    -0.65
    olkien
    -0.64
    Footnote
    -0.64
    sylv
    -0.64
    POSITIVE LOGITS
     stairs
    0.99
    stairs
    0.96
    graded
    0.94
    river
    0.94
    grading
    0.83
     sidx
    0.80
     knees
    0.73
    grades
    0.71
     crashing
    0.71
    vote
    0.71
    Activations Density 0.021%

    No Known Activations