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. 22083
    Prev
    Next
    INDEX
    Explanations

    references to sources or citations

    oai_token-act-pair · gpt-3.5-turbo

    references to reputable sources of information

    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
    aeper
    -0.69
    TAG
    -0.66
    oos
    -0.66
    Ħ¢
    -0.64
    boxing
    -0.64
    otos
    -0.63
    roe
    -0.62
    olded
    -0.61
    STRUCT
    -0.60
    âĶģ
    -0.59
    POSITIVE LOGITS
    ources
    1.19
    ourcing
    1.16
     sources
    1.09
     Sources
    1.01
    etter
    1.01
    ourced
    0.93
    afe
    0.92
    cale
    0.88
     consulted
    0.87
    hips
    0.86
    Activations Density 0.040%

    No Known Activations