INDEX

Explanations

the term "data" in various contexts, particularly in legal and technical references related to liabilities and consequences

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

our

-1.71

Our

-1.68

 Connecticut

-1.62

 Wyoming

-1.53

arsh

-1.53

-1.50

cluding

-1.49

astern

-1.48

vereign

-1.47

us

-1.42

POSITIVE LOGITS

CRIPT

1.80

Ã§o

1.73

iliary

1.68

Ã±o

1.66

imo

1.57

esan

1.56

rooms

1.56

CRIPTION

1.55

Rptr

1.55

ucci

1.55

Activations Density 0.022%

the term "data" in various contexts, particularly in legal and technical references related to liabilities and consequences

No Comments

No Known Activations