INDEX

Explanations

the term "lex" in various contexts, indicating a focus on lexical or language-related concepts

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.0.hook_mlp_out

Hook Layer

Architecture

standard

Context Size

128

Dataset

EleutherAI/the_pile_deduplicated

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 else

-2.21

inner

-1.65

res

-1.59

"?"

-1.47

illed

-1.46

 taste

-1.46

odot

-1.45

)){

-1.42

 suppose

-1.42

;&

-1.41

POSITIVE LOGITS

enos

1.80

igent

1.73

ibase

1.71

imab

1.70

cores

1.68

ig

1.67

plicit

1.65

ball

1.62

volt

1.57

ibo

1.56

Activations Density 0.013%

the term "lex" in various contexts, indicating a focus on lexical or language-related concepts

No Comments

No Known Activations