Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 23600
    Prev
    Next
    INDEX
    Explanations

    references to the character "Gandalf" from "The Lord of the Rings" series

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Gandalf" from the "Lord of the Rings" franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     posit
    -0.69
     packed
    -0.65
     Tec
    -0.64
     PAN
    -0.61
     confess
    -0.61
     ÃĹ
    -0.60
     cos
    -0.59
     Pon
    -0.59
     pop
    -0.59
     Prec
    -0.58
    POSITIVE LOGITS
    alf
    5.01
    als
    1.45
    elf
    1.28
    olf
    1.21
    alg
    1.19
    ald
    1.19
    ale
    1.17
    arb
    1.09
    ALS
    1.07
    alth
    1.05
    Activations Density 0.006%

    No Known Activations