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. 7113
    Prev
    Next
    INDEX
    Explanations

    words related to strengthening, support, or making something stronger

    oai_token-act-pair · gpt-3.5-turbo

    words related to reinforcement and related concepts

    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
    kie
    -0.74
    cture
    -0.72
    NetMessage
    -0.72
    kers
    -0.72
    chens
    -0.71
    izons
    -0.71
    «ĺ
    -0.70
    enne
    -0.69
    bright
    -0.69
    soever
    -0.68
    POSITIVE LOGITS
     reinforcing
    1.23
     reinforcement
    1.06
     reinforced
    0.89
     reinforce
    0.81
    ments
    0.81
     additive
    0.75
    forcement
    0.71
     reinforces
    0.70
    undown
    0.69
    forcing
    0.69
    Activations Density 0.027%

    No Known Activations