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. 4957
    Prev
    Next
    INDEX
    Explanations

    mentions of political and economic topics such as governmental actions, sanctions, financial ties, and economic conditions

    oai_token-act-pair · gpt-3.5-turbo

    end punctuation marks, indicating the conclusion of statements

    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
     millenn
    -0.80
     misunderstood
    -0.71
     killers
    -0.67
     trainers
    -0.65
     facult
    -0.65
     secretaries
    -0.64
     hospitality
    -0.64
     trainer
    -0.64
     essentials
    -0.63
     margins
    -0.62
    POSITIVE LOGITS
    ðĿ
    0.92
    ossus
    0.88
    soon
    0.88
    tel
    0.84
    Pa
    0.81
    ORGE
    0.78
    -.
    0.76
    once
    0.76
    which
    0.75
    then
    0.75
    Activations Density 0.063%

    No Known Activations