INDEX

Explanations

proper nouns or titles preceded by the word "the"

oai_token-act-pair · gpt-3.5-turbo

instances 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

eno

-0.79

iably

-0.75

leeve

-0.73

ï¿½ï¿½ï¿½ï¿½

-0.73

govtrack

-0.69

whatever

-0.68

âĹ¼

-0.67

akable

-0.67

tackle

-0.67

abuse

-0.67

POSITIVE LOGITS

 remainder

1.18

oret

1.08

 largest

1.05

 earliest

1.03

 entire

1.01

 following

1.00

 newest

1.00

 goal

0.98

 purpose

0.96

 latest

0.96

Activations Density 0.478%

proper nouns or titles preceded by the word "the"

instances of the word "The."

No Comments

No Known Activations