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. 5150
    Prev
    Next
    INDEX
    Explanations

    statements that are presented as facts

    oai_token-act-pair · gpt-3.5-turbo

    references to factual statements or claims

    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
    avorite
    -0.79
     Klux
    -0.79
    jri
    -0.76
    isoft
    -0.71
    artney
    -0.69
    ModLoader
    -0.69
    interstitial
    -0.69
    ctic
    -0.68
    hod
    -0.68
     Carbuncle
    -0.67
    POSITIVE LOGITS
    ually
    1.26
    orial
    1.15
    itious
    1.05
    ional
    1.03
    oids
    0.99
    ially
    0.94
    uality
    0.92
    ual
    0.91
    oid
    0.88
    icity
    0.86
    Activations Density 0.029%

    No Known Activations