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. 2824
    Prev
    Next
    INDEX
    Explanations

    words related to traditional or old-fashioned practices or objects

    oai_token-act-pair · gpt-3.5-turbo

    words associated with traditional or classic styles

    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
    ese
    -0.83
    esville
    -0.81
    urrent
    -0.76
    worthiness
    -0.73
    hip
    -0.71
    anon
    -0.71
    board
    -0.69
    itor
    -0.69
    ity
    -0.68
    ysis
    -0.67
    POSITIVE LOGITS
     srfAttach
    0.74
    Īè
    0.71
     adolesc
    0.71
     conflic
    0.70
    л
    0.69
    Ī
    0.69
     disadvant
    0.69
    ĸļ
    0.69
    chin
    0.65
    eners
    0.65
    Activations Density 0.045%

    No Known Activations