© 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. 15218
    Prev
    Next
    INDEX
    Explanations

    sentences expressing personal experiences or emotions

    oai_token-act-pair · gpt-3.5-turbo

    the verb "to be" in various forms

    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
    osate
    -0.71
     undertook
    -0.70
     Achieve
    -0.70
     claimants
    -0.69
    ilst
    -0.67
    icipated
    -0.66
     cite
    -0.65
    udeau
    -0.65
    wrote
    -0.65
     campaigner
    -0.64
    POSITIVE LOGITS
     gonna
    1.21
    nt
    1.09
     definitely
    1.02
     probably
    0.94
     going
    0.90
     awesome
    0.89
     amazing
    0.89
    wolves
    0.88
     supposed
    0.88
     kinda
    0.87
    Activations Density 0.721%

    No Known Activations