INDEX

Explanations

pronouns 'They' or 'they' referring to unidentified persons or entities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the pronoun "they"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.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

VW

-0.70

paragraph

-0.70

 Eleven

-0.70

church

-0.69

 Club

-0.69

 Globe

-0.69

Sao

-0.67

CCC

-0.67

_______

-0.66

 Windsor

-0.64

POSITIVE LOGITS

're

1.15

'll

0.91

zbollah

0.86

've

0.86

'd

0.85

mos

0.83

uristic

0.77

IPP

0.77

ngth

0.76

illac

0.73

Activations Density 0.216%

pronouns 'They' or 'they' referring to unidentified persons or entities

occurrences of the pronoun "they"

No Comments

No Known Activations