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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 18511
    Prev
    Next
    INDEX
    Explanations

    proper names starting with "Ren" and followed by a high numeric value

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the name "Ren" in the text

    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
    stakes
    -0.84
    HAEL
    -0.75
    OOL
    -0.71
    Ö¼
    -0.69
     Antar
    -0.68
     NETWORK
    -0.68
    milo
    -0.68
     اÙĦ
    -0.66
    =-=-
    -0.66
    trak
    -0.65
    POSITIVE LOGITS
    unciation
    1.12
    issance
    1.10
    unci
    1.06
    ovation
    1.05
    aming
    0.94
    emy
    0.93
    ault
    0.91
    ouncing
    0.90
    owned
    0.89
    ochet
    0.89
    Activations Density 0.010%

    No Known Activations