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. 699
    Prev
    Next
    INDEX
    Explanations

    references to the word "ram" or related words (e.g., cram, lugging)

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of 'ram' and associated actions or descriptions that include 'cram' and 'lug'

    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
     Vald
    -0.73
    IELD
    -0.73
    CLASSIFIED
    -0.71
     Cind
    -0.71
     Valerie
    -0.71
     Bind
    -0.70
     Towers
    -0.70
    ACP
    -0.68
    Ô
    -0.65
     Knight
    -0.65
    POSITIVE LOGITS
     ram
    1.18
    ming
    1.03
    dump
    0.81
    bling
    0.80
    disk
    0.80
    ble
    0.78
    itating
    0.78
     cram
    0.77
    herent
    0.76
    orously
    0.74
    Activations Density 0.024%

    No Known Activations