© 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. 4-RES-JB
    11. 3638
    Prev
    Next
    INDEX
    Explanations

    phrases related to innovative technologies or systems

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "that," often indicating clauses or descriptions

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

    No Comments

    Negative Logits
    WARE
    -0.65
     Alive
    -0.64
     Eye
    -0.62
     Doctrine
    -0.61
     Corps
    -0.60
     Gallery
    -0.59
    Gy
    -0.57
    ysis
    -0.57
     Standing
    -0.57
    hat
    -0.57
    POSITIVE LOGITS
     arose
    0.97
     accompanies
    0.93
     resulted
    0.91
     extends
    0.86
    soever
    0.84
     promotes
    0.83
     creates
    0.83
     produces
    0.82
     surrounds
    0.82
     culminated
    0.81
    Activations Density 0.274%

    No Known Activations