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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 23048
    Prev
    Next
    INDEX
    Explanations

    forms of the word "have" following certain contextual cues

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express conditional situations or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fireball
    -0.66
    catentry
    -0.66
    ocol
    -0.65
    osa
    -0.59
     wrapping
    -0.58
     tracing
    -0.57
    rift
    -0.55
     proclaiming
    -0.54
     Grape
    -0.54
     territ
    -0.54
    POSITIVE LOGITS
     been
    1.32
    been
    1.12
     gotten
    1.11
     Been
    1.08
    gotten
    1.03
     undergone
    0.93
     gone
    0.91
     seen
    0.88
     come
    0.88
     taken
    0.87
    Activations Density 0.143%

    No Known Activations