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. 19935
    Prev
    Next
    INDEX
    Explanations

    references to the plant Ayahuasca and related entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific names, particularly related to "Ayahuasca" and geopolitical terms

    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
     Indust
    -0.64
     vein
    -0.63
     Thumbnails
    -0.62
     nod
    -0.62
    LAB
    -0.61
    case
    -0.59
    piece
    -0.59
     CLIENT
    -0.58
     Correction
    -0.58
    dress
    -0.58
    POSITIVE LOGITS
    asca
    1.24
    ahu
    1.16
    isance
    1.15
    atl
    0.95
    ulhu
    0.92
    aii
    0.89
    actus
    0.89
    estic
    0.88
    ierrez
    0.86
    anced
    0.81
    Activations Density 0.022%

    No Known Activations