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. 23807
    Prev
    Next
    INDEX
    Explanations

    the name "Fred"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Fred."

    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
    BOOK
    -0.78
     inhibitors
    -0.68
    ĵĺ
    -0.67
    Demand
    -0.67
     distingu
    -0.65
     compr
    -0.64
    ModLoader
    -0.63
     forth
    -0.63
     compounded
    -0.62
    chnology
    -0.62
    POSITIVE LOGITS
    rik
    1.18
    erick
    1.13
    rick
    1.12
    rique
    1.09
    dy
    1.06
    ric
    1.03
    ricks
    1.00
    dies
    0.99
    riks
    0.97
    die
    0.96
    Activations Density 0.009%

    No Known Activations