INDEX

Explanations

sentences with pronouns referring to groups of people

oai_token-act-pair · gpt-3.5-turbo

pronouns indicating people and their actions in a narrative context

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

pires

-0.87

tains

-0.75

 Innocent

-0.69

uates

-0.68

âĦ¢:

-0.67

osphere

-0.64

opathy

-0.64

olit

-0.62

iates

-0.61

 Immunity

-0.61

POSITIVE LOGITS

 waited

1.03

 searched

1.02

 didn

0.99

 hadn

0.98

 knew

0.96

saw

0.96

 didnt

0.95

 glanced

0.95

 woke

0.95

'd

0.94

Activations Density 0.380%

sentences with pronouns referring to groups of people

pronouns indicating people and their actions in a narrative context

No Known Activations