INDEX

Explanations

proper nouns introduced by the word "said"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "said."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

à¦

-0.87

²¾

-0.84

otin

-0.74

agra

-0.71

Ø¹

-0.71

-0.68

estern

-0.68

enza

-0.65

oto

-0.65

eneg

-0.65

POSITIVE LOGITS

 analysts

0.91

 sources

0.85

 analyst

0.82

 spokeswoman

0.80

 spokesman

0.79

 Pamela

0.75

 organizers

0.74

 Alexa

0.74

KR

0.72

 Donna

0.71

Activations Density 0.080%

proper nouns introduced by the word "said"

instances of the word "said."

No Comments

No Known Activations