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. 19906
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Esc" followed by a number between 7 and 10

    oai_token-act-pair · gpt-3.5-turbo

    the name "Escobar" in various contexts

    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
    ãĥĩãĤ£
    -0.91
    è»
    -0.72
    åĤ
    -0.71
    çİĭ
    -0.69
    å§«
    -0.68
    beard
    -0.68
    gaard
    -0.68
    WARE
    -0.68
    ãģ®éŃĶ
    -0.68
     Dynamics
    -0.66
    POSITIVE LOGITS
    ribed
    1.16
    apist
    1.06
    orts
    0.98
    apes
    0.98
    aped
    0.97
    ription
    0.95
    ades
    0.94
    ounters
    0.93
     Esc
    0.91
    adr
    0.89
    Activations Density 0.012%

    No Known Activations