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

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 22209
    Prev
    Next
    INDEX
    Explanations

    mentions of RAM (Random Access Memory)

    oai_token-act-pair · gpt-3.5-turbo

    terms related to computer memory specifications, particularly RAM

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramer
    -0.75
     Burnett
    -0.68
     Gw
    -0.67
     Spit
    -0.65
    reek
    -0.59
    ernel
    -0.56
     Hazel
    -0.55
     Byrd
    -0.55
     Georg
    -0.55
     indifference
    -0.55
    POSITIVE LOGITS
    ming
    1.19
    mers
    1.06
    der
    1.02
    senal
    0.88
    aic
    0.87
    DAY
    0.86
    irez
    0.85
    med
    0.84
    seys
    0.82
    ORPG
    0.82
    Activations Density 0.075%

    No Known Activations