INDEX

Explanations

questions and statements related to uncertainty and evaluation of situations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ..."

-0.63

)."

-0.61

?".

-0.57

 guiActiveUnfocused

-0.56

]."

-0.55

.","

-0.52

".[

-0.51

Chain

-0.50

..."

-0.50

Due

-0.49

POSITIVE LOGITS

 Chomsky

0.66

 irony

0.65

 analogy

0.61

 Orwell

0.59

 anecdote

0.57

iberal

0.57

 Slate

0.57

 Cohn

0.56

 Rosenberg

0.56

 Krugman

0.55

Activations Density 0.734%

questions and statements related to uncertainty and evaluation of situations

No Comments

No Known Activations