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. 5423
    Prev
    Next
    INDEX
    Explanations

    words related to specific interests or hobbies, particularly involving technology or community gatherings

    oai_token-act-pair · gpt-3.5-turbo

    references to various groups of enthusiasts across different interests

    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
    tein
    -0.71
    ãĥĥãĥī
    -0.68
     Pesh
    -0.64
     Walls
    -0.64
    downs
    -0.62
     Khe
    -0.60
    outs
    -0.59
    emb
    -0.59
    lining
    -0.59
    met
    -0.59
    POSITIVE LOGITS
     hobby
    0.89
    ORPG
    0.80
     enthusiasts
    0.79
    sonian
    0.78
    ateurs
    0.77
     rpm
    0.77
    ateur
    0.77
     flock
    0.77
    £ı
    0.74
     enthusiast
    0.71
    Activations Density 0.019%

    No Known Activations