© 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. 4-RES-JB
    11. 15279
    Prev
    Next
    INDEX
    Explanations

    keywords related to the physical aspects of an object's outer surface

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the physical attributes and design of exteriors and horizontal elements in structures

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

    No Comments

    Negative Logits
    rd
    -1.12
    otle
    -0.88
    iasco
    -0.87
    uncture
    -0.86
    etic
    -0.83
    alez
    -0.82
    hetti
    -0.82
    oos
    -0.78
    aque
    -0.78
    enegger
    -0.78
    POSITIVE LOGITS
    soever
    0.76
     thirds
    0.76
    ipop
    0.75
    ascus
    0.71
     Ukrain
    0.70
    nd
    0.65
    selves
    0.65
     assail
    0.64
     Lip
    0.64
     mete
    0.63
    Activations Density 0.069%

    No Known Activations