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. 6-RES-JB
    6. 2106
    Prev
    Next
    INDEX
    Explanations

    words related to sequencing or sequencers

    oai_token-act-pair · gpt-3.5-turbo

    words related to sequencing or categorizing elements in a structured manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ukrainians
    -0.68
    HAEL
    -0.68
     Ukrainian
    -0.67
    Downloadha
    -0.67
    GROUND
    -0.65
    ¿½
    -0.65
     intens
    -0.64
    ModLoader
    -0.62
     Imran
    -0.62
     Olympia
    -0.62
    POSITIVE LOGITS
    enced
    1.44
    encer
    1.31
    entially
    1.24
    encing
    1.14
    ences
    1.13
    encers
    1.05
    pta
    1.03
    ential
    1.01
    ester
    0.97
    ination
    0.96
    Activations Density 0.021%

    No Known Activations