INDEX

Explanations

words with the prefix "re-" followed by an action or concept

oai_token-act-pair · gpt-3.5-turbo

words related to prefixes denoting a state or condition, especially those starting with "ac" or "en."

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

 shorth

-0.80

Spa

-0.75

EVA

-0.72

 Piper

-0.69

Kot

-0.68

 Christensen

-0.68

 shaved

-0.66

Cot

-0.66

Gap

-0.65

 Shots

-0.65

POSITIVE LOGITS

minent

1.05

ertain

1.03

ception

1.03

mosp

1.01

ploy

1.00

usterity

0.98

istant

0.97

terior

0.97

emption

0.96

velop

0.95

Activations Density 0.124%

words with the prefix "re-" followed by an action or concept

words related to prefixes denoting a state or condition, especially those starting with "ac" or "en."

No Comments

No Known Activations