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. 22877
    Prev
    Next
    INDEX
    Explanations

    quotations and phrases enclosed by single quotes and 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate significant actions or events related to economic situations

    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
    geons
    -0.86
    llular
    -0.81
    swer
    -0.75
     ENT
    -0.70
    ror
    -0.69
    thur
    -0.66
    hedon
    -0.66
    arant
    -0.65
    brate
    -0.64
    enium
    -0.64
    POSITIVE LOGITS
    ccording
    1.03
    JUST
    0.86
    Experts
    0.77
    FACE
    0.76
    Meanwhile
    0.74
    Across
    0.72
    Speaking
    0.70
    Born
    0.70
    Since
    0.69
    Aid
    0.68
    Activations Density 0.150%

    No Known Activations