© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9512
    Prev
    Next
    INDEX
    Explanations

    adjectives or phrases related to a short duration

    oai_token-act-pair · gpt-3.5-turbo

    references to short durations or brief experiences

    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
    ILLE
    -0.74
    velt
    -0.70
    itational
    -0.70
    IRO
    -0.68
    ICAN
    -0.64
    KI
    -0.64
    JV
    -0.64
    Magikarp
    -0.64
    IAN
    -0.63
    Gener
    -0.63
    POSITIVE LOGITS
    short
    1.02
    sighted
    0.95
    ening
    0.92
    ened
    0.88
    sword
    0.84
    comings
    0.84
     stature
    0.82
    lived
    0.81
    bread
    0.81
    leaf
    0.80
    Activations Density 0.018%

    No Known Activations