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. 373
    Prev
    Next
    INDEX
    Explanations

    references to paranormal and supernatural phenomena

    oai_token-act-pair · gpt-3.5-turbo

    references to paranormal and supernatural concepts

    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
    oglu
    -0.85
    Ô
    -0.82
    fed
    -0.77
    ļéĨĴ
    -0.74
    cdn
    -0.70
    DN
    -0.67
    TAIN
    -0.67
    bern
    -0.67
    mil
    -0.67
    Effective
    -0.66
    POSITIVE LOGITS
     haunted
    0.94
     haunting
    0.92
     hallucinations
    0.91
    Haunted
    0.90
     psychic
    0.90
     paranormal
    0.89
     haunt
    0.88
     Haunted
    0.86
    ormal
    0.83
     wand
    0.82
    Activations Density 0.199%

    No Known Activations