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. 0-RES-JB
    6. 8467
    Prev
    Next
    INDEX
    Explanations

    references to computer memory (RAM)

    oai_token-act-pair · gpt-3.5-turbo

    references to RAM and related computing terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Evolution
    -0.74
     derby
    -0.67
     Mach
    -0.67
     Mor
    -0.67
     Fowler
    -0.67
     Fe
    -0.67
     Engel
    -0.65
    ãĤ¢ãĥ«
    -0.65
     Akin
    -0.65
     Ev
    -0.64
    POSITIVE LOGITS
    RAM
    3.81
    ROM
    1.44
    amba
    1.36
    SAM
    1.31
    SAN
    1.28
    LU
    1.28
    RY
    1.22
    LAN
    1.17
     ANGEL
    1.14
    Memory
    1.10
    Activations Density 0.040%

    No Known Activations