INDEX

Explanations

phrases related to future plans or intentions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the phrase "planning on."

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

ACT

-0.78

ï¸ı

-0.75

Bridge

-0.73

sworth

-0.71

displayText

-0.70

 Monitor

-0.68

wine

-0.67

externalActionCode

-0.67

SPA

-0.67

UST

-0.67

POSITIVE LOGITS

 behalf

0.97

erous

0.96

 preserving

0.86

 arrival

0.84

 sticking

0.78

 stopping

0.74

seeing

0.74

eday

0.73

 occas

0.72

 immortality

0.72

Activations Density 0.061%

phrases related to future plans or intentions

occurrences of the phrase "planning on."

No Comments

No Known Activations