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. 7153
    Prev
    Next
    INDEX
    Explanations

    phrases related to having the ability to reach a certain resource or information

    oai_token-act-pair · gpt-3.5-turbo

    references to access, particularly in the context of information or services

    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
    NR
    -0.82
    boxing
    -0.80
    NL
    -0.79
    soDeliveryDate
    -0.77
    need
    -0.74
    ernand
    -0.73
    roit
    -0.72
    okia
    -0.71
    Äĩ
    -0.71
    KK
    -0.69
    POSITIVE LOGITS
     assist
    0.66
     minim
    0.66
     preserve
    0.66
     resources
    0.66
     recess
    0.64
     access
    0.64
    itives
    0.64
     prevent
    0.63
     lift
    0.62
     riches
    0.61
    Activations Density 0.062%

    No Known Activations