© 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. 2-RES-JB
    11. 17783
    Prev
    Next
    INDEX
    Explanations

    words related to tracking or following something closely

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "tr."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ELS
    -0.88
    MENTS
    -0.71
    EStream
    -0.71
    EL
    -0.63
     tightening
    -0.63
    BILITIES
    -0.62
    ORED
    -0.62
     arts
    -0.62
    EEE
    -0.61
     doubling
    -0.60
    POSITIVE LOGITS
    ainer
    1.08
    itton
    1.07
    unk
    1.06
    ilateral
    1.06
    agic
    1.01
    unks
    1.00
    acker
    0.97
    acers
    0.96
    acement
    0.96
    umps
    0.96
    Activations Density 0.008%

    No Known Activations