© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 9510
    Prev
    Next
    INDEX
    Explanations

    terms related to technology, particularly to ROM and PCB components

    oai_token-act-pair · gpt-3.5-turbo

    references to ROM (Read-Only Memory) in various contexts

    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
    Irish
    -0.78
    raviolet
    -0.74
     Byrd
    -0.72
     brewing
    -0.70
     Irish
    -0.69
    ker
    -0.68
     Blackhawks
    -0.66
    netflix
    -0.64
    ibel
    -0.64
    nel
    -0.64
    POSITIVE LOGITS
     ROM
    1.32
    ROM
    1.08
    UX
    0.82
     corrid
    0.79
    DAY
    0.78
    ORED
    0.77
     resil
    0.75
    ONY
    0.74
    anmar
    0.73
     emulator
    0.72
    Activations Density 0.014%

    No Known Activations