© 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. 13879
    Prev
    Next
    INDEX
    Explanations

    terms related to exponential growth

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conflict or competition

    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
     Zac
    -0.53
    ĵĺ
    -0.51
    ovember
    -0.50
     Brist
    -0.49
     Volunte
    -0.46
    Kick
    -0.46
    tags
    -0.45
     Fraz
    -0.45
     Hug
    -0.43
     Jub
    -0.43
    POSITIVE LOGITS
    ongyang
    0.55
    ohm
    0.53
    bard
    0.53
    enhagen
    0.52
    apore
    0.50
    yang
    0.49
    brids
    0.48
    inces
    0.47
    endif
    0.47
    osuke
    0.46
    Activations Density 2.081%

    No Known Activations