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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 14611
    Prev
    Next
    INDEX
    Explanations

    phrases related to creating or building

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "making."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vest
    -0.74
     Mub
    -0.65
    ---------
    -0.60
    thia
    -0.60
     Shannon
    -0.60
    ban
    -0.60
     conditioning
    -0.59
     Dominican
    -0.58
     Suit
    -0.58
     scrimmage
    -0.57
    POSITIVE LOGITS
    awaru
    0.91
    hift
    0.88
     sure
    0.83
    ailable
    0.83
    emort
    0.82
    itives
    0.79
    akable
    0.77
    amera
    0.75
    itions
    0.72
    ÄŁ
    0.72
    Activations Density 0.051%

    No Known Activations