© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 16282
    Prev
    Next
    INDEX
    Explanations

    references to computer hardware specifications, particularly the amount of RAM

    oai_token-act-pair · gpt-3.5-turbo

    references to RAM and memory specifications in devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reek
    -0.75
     Foley
    -0.71
     Indo
    -0.71
    legraph
    -0.69
     Daniels
    -0.68
    kef
    -0.67
     Australian
    -0.67
     degree
    -0.63
    coord
    -0.63
     Tennessee
    -0.63
    POSITIVE LOGITS
     RAM
    1.01
    disk
    0.96
    PDATE
    0.86
    irez
    0.85
    dump
    0.82
    Disk
    0.82
    mers
    0.80
    RAM
    0.77
    ming
    0.77
    matical
    0.75
    Activations Density 0.005%

    No Known Activations