INDEX

Explanations

instances of the term "word" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-1.08

 Monfieur

-0.99

 himſelf

-0.98

%]

-0.98

 pleaſure

-0.98

"]];

-0.97

 photolibrary

-0.97

"]]

-0.95

."));

-0.93

 يتيمه

-0.93

POSITIVE LOGITS

 words

1.66

 Words

1.57

 Word

1.53

 word

1.50

Word

1.46

 WORD

1.45

Words

1.39

 WORDS

1.38

words

1.31

word

1.30

Activations Density 0.052%

instances of the term "word" and its variations in various contexts

No Comments

No Known Activations