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. 14000
    Prev
    Next
    INDEX
    Explanations

    words related to filmmaking and movie-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Fil" or its variations

    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
    anwhile
    -0.76
    è¦ļéĨĴ
    -0.72
     compr
    -0.69
    ELL
    -0.67
     Butterfly
    -0.66
    schild
    -0.65
     convict
    -0.64
     digest
    -0.63
    eanor
    -0.62
    JV
    -0.62
    POSITIVE LOGITS
    tered
    1.19
    ters
    1.17
    igree
    1.06
    tering
    1.05
    thy
    1.02
    terness
    0.98
    eno
    0.94
    fil
    0.93
    Fil
    0.92
    teenth
    0.91
    Activations Density 0.009%

    No Known Activations