© 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. 3-RES-JB
    11. 15165
    Prev
    Next
    INDEX
    Explanations

    instances where something is moving or progressing beyond a particular point

    oai_token-act-pair · gpt-3.5-turbo

    the word "past" and its various contexts

    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
    anguage
    -0.76
    hyde
    -0.66
    Software
    -0.65
    zh
    -0.64
    lee
    -0.63
    Services
    -0.63
    hz
    -0.62
    NEY
    -0.62
    DH
    -0.62
    udden
    -0.62
    POSITIVE LOGITS
    ebin
    1.40
    iche
    0.90
     midnight
    0.85
     tense
    0.83
     generations
    0.81
    ures
    0.77
     past
    0.72
    ime
    0.71
     week
    0.70
    İ
    0.68
    Activations Density 0.027%

    No Known Activations