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. 24367
    Prev
    Next
    INDEX
    Explanations

    financial and numerical information

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols present in the text

    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
    oted
    -0.78
    otion
    -0.66
     ancest
    -0.64
     silhou
    -0.64
    umbn
    -0.63
     interf
    -0.63
     Pony
    -0.63
     menstru
    -0.61
     limb
    -0.61
     Peb
    -0.60
    POSITIVE LOGITS
    âĤ¬
    1.10
    ï
    0.88
    ¢
    0.88
    Ëľ
    0.87
    hyde
    0.83
    £
    0.82
    ç
    0.77
    rica
    0.77
     âĤ¬
    0.76
    vre
    0.75
    Activations Density 0.004%

    No Known Activations