Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 493
    Prev
    Next
    INDEX
    Explanations

    the word "coherent" and its derivations

    oai_token-act-pair · gpt-4-turbo

    adjectives related to coherence or incoherence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to coherence and cohesion in narratives or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     1936
    -0.67
    geon
    -0.66
     Ern
    -0.65
    AMI
    -0.65
    von
    -0.63
    ALT
    -0.62
    OUT
    -0.62
    TL
    -0.61
    enge
    -0.61
    tu
    -0.61
    POSITIVE LOGITS
    herent
    1.14
     coherent
    1.08
    ively
    0.99
    herence
    0.96
    ly
    0.92
    jriwal
    0.92
     inco
    0.90
     cohesion
    0.89
    nesses
    0.86
    hesive
    0.82
    Activations Density 0.021%

    No Known Activations