© 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. 1-RES-JB
    11. 5552
    Prev
    Next
    INDEX
    Explanations

    references to significant events or concepts like economic collapses

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "collapse."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qua
    -0.78
    given
    -0.72
    Choice
    -0.71
    \":
    -0.71
    gran
    -0.70
    cil
    -0.70
    cial
    -0.70
    chie
    -0.69
    ĭ
    -0.68
    pir
    -0.68
    POSITIVE LOGITS
     collapse
    1.21
     collapses
    1.09
     inertia
    0.89
     collapsing
    0.88
     downfall
    0.85
     meltdown
    0.85
     tremend
    0.84
     crumble
    0.83
    ulence
    0.80
     collapsed
    0.80
    Activations Density 0.009%

    No Known Activations