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. 5841
    Prev
    Next
    INDEX
    Explanations

    quotations within a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of direct quotations or speech in the text

    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
     scheduled
    -0.83
     cannabin
    -0.82
     adjud
    -0.81
     favor
    -0.77
     schedule
    -0.73
     graded
    -0.72
     resettlement
    -0.71
     surfaced
    -0.71
     midterm
    -0.70
     distingu
    -0.70
    POSITIVE LOGITS
    We
    1.15
    I
    1.10
    Our
    1.05
    Hey
    1.02
    heter
    1.00
    Dear
    0.99
    Everyone
    0.99
    Absolutely
    0.97
    Walk
    0.96
    It
    0.96
    Activations Density 0.081%

    No Known Activations