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. 9485
    Prev
    Next
    INDEX
    Explanations

    patterns of characters that suggest URLs or links

    oai_token-act-pair · gpt-3.5-turbo

    words related to chocolate and its quality or condition

    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
    buster
    -0.76
     VIEW
    -0.74
     Hutchinson
    -0.69
     buckle
    -0.66
    VK
    -0.65
     figure
    -0.64
     WOR
    -0.64
     Grayson
    -0.63
     Forsaken
    -0.63
     Feldman
    -0.63
    POSITIVE LOGITS
    onial
    1.16
    ocol
    1.00
    atem
    0.99
    acco
    0.98
    avored
    0.93
    urized
    0.91
    oria
    0.89
    orius
    0.87
    ongyang
    0.85
    ates
    0.85
    Activations Density 0.026%

    No Known Activations