INDEX

Explanations

phrases where the word 'said' is used

oai_token-act-pair · gpt-3.5-turbo

the word "said" in various contexts, indicating speech or statements made by individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

otion

-0.69

pleting

-0.67

otin

-0.67

\/\/

-0.66

à¦

-0.65

izont

-0.63

equipped

-0.61

PHOTOS

-0.61

ooter

-0.60

POSITIVE LOGITS

 sarcast

0.72

 goodbye

0.71

 bluntly

0.70

doms

0.70

 said

0.66

 anecd

0.64

 earlier

0.61

 yesterday

0.61

 plaint

0.60

 gloom

0.57

Activations Density 0.153%

phrases where the word 'said' is used

the word "said" in various contexts, indicating speech or statements made by individuals

No Comments

No Known Activations