INDEX

Explanations

occurrences of the term "Se," which may indicate a focus on specific sequences or references in a broader context

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.1.hook_resid_post

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

ses

-1.93

tons

-1.92

sis

-1.81

actic

-1.74

soever

-1.64

sch

-1.57

onymous

-1.56

ounced

-1.53

 footsteps

-1.53

ted

-1.51

POSITIVE LOGITS

«

2.45

¯

2.25

½

2.02

·

1.97

¿

1.86

©

1.84

ĸ

1.78

·¸

1.77

¹

1.74

Īĺ

1.73

Activations Density 0.063%

occurrences of the term "Se," which may indicate a focus on specific sequences or references in a broader context

No Comments

No Known Activations