© 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. 3660
    Prev
    Next
    INDEX
    Explanations

    instances where something or someone is suspended

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "suspended" in various contexts

    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
    rics
    -0.81
     originals
    -0.72
    ortment
    -0.71
    åĮ
    -0.70
    PRES
    -0.70
    ãģ®æ
    -0.69
    wer
    -0.66
    eus
    -0.66
    WARD
    -0.65
    raltar
    -0.65
    POSITIVE LOGITS
     indefinitely
    1.06
     suspended
    1.06
     suspending
    1.04
     disbelief
    1.00
     suspensions
    0.94
     suspension
    0.93
     suspend
    0.91
     susp
    0.86
    ©¶æ¥µ
    0.79
    owship
    0.75
    Activations Density 0.014%

    No Known Activations