INDEX

Explanations

words related to wordplay and language

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "word" or "words."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

cffff

-0.80

asio

-0.75

DERR

-0.74

psey

-0.72

awaru

-0.71

itant

-0.70

kens

-0.70

abama

-0.70

etheus

-0.70

âĹ¼

-0.67

POSITIVE LOGITS

press

1.10

sworth

1.06

ifier

0.86

 word

0.85

ptr

0.84

word

0.83

 processor

0.81

naire

0.80

 Word

0.77

edly

0.77

Activations Density 0.024%

words related to wordplay and language

references to the concept of "word" or "words."

No Comments

No Known Activations