INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

Not in Any Lists

No Comments

Negative Logits

abuse

-0.79

apon

-0.76

each

-0.76

ambo

-0.73

rooms

-0.70

 exists

-0.69

sheets

-0.68

 existed

-0.68

their

-0.67

mares

-0.67

POSITIVE LOGITS

 largest

1.34

 culmination

1.28

 fastest

1.21

 latest

1.21

 easiest

1.19

 biggest

1.18

 oldest

1.18

 strongest

1.16

 heaviest

1.15

 widest

1.14

Activations Density 0.165%

proper nouns

occurrences of the word "the."

No Comments

No Known Activations