© 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. 0-RES-JB
    11. 4055
    Prev
    Next
    INDEX
    Explanations

    words related to actions or items associated with a specific function or purpose

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions or processes, especially those that denote physical movement or transfer

    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
     lin
    -0.63
     kale
    -0.63
     socks
    -0.62
     hiding
    -0.62
     stocks
    -0.61
     Elf
    -0.60
     sequ
    -0.59
     mel
    -0.59
     Luk
    -0.57
     recess
    -0.57
    POSITIVE LOGITS
    ction
    4.77
    ctions
    3.09
    ctive
    2.18
    ctor
    1.71
    ct
    1.58
    ctory
    1.47
    ctors
    1.23
    cture
    1.22
    gment
    1.16
    tion
    1.12
    Activations Density 0.016%

    No Known Activations