INDEX

Explanations

proper names or terms related to universities and professionals

oai_token-act-pair · gpt-3.5-turbo

adjectives that imply a sense of quality or condition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 EDITION

-0.66

è¦ļéĨĴ

-0.62

 Grimes

-0.60

 parentheses

-0.60

BOOK

-0.57

 Starship

-0.57

OWS

-0.57

ODY

-0.56

 PowerPoint

-0.56

ANK

-0.56

POSITIVE LOGITS

sein

1.00

sin

0.96

ivil

0.94

say

0.89

sa

0.88

eh

0.87

gue

0.86

uke

0.86

quet

0.85

 vide

0.85

Activations Density 0.051%

proper names or terms related to universities and professionals

adjectives that imply a sense of quality or condition

No Comments

No Known Activations