INDEX

Explanations

references to the concept of "Thinking" or reflecting

oai_token-act-pair · gpt-3.5-turbo

prompts that encourage reflection or consideration

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

cffffcc

-0.71

iqueness

-0.71

 Adin

-0.69

taboola

-0.67

GMT

-0.66

conservancy

-0.64

Interstitial

-0.64

recorded

-0.62

CBC

-0.62

Merit

-0.62

POSITIVE LOGITS

ileaks

0.77

ative

0.72

notations

0.71

iste

0.70

lahoma

0.70

pad

0.70

onymous

0.69

ventus

0.69

eport

0.68

itia

0.67

Activations Density 0.033%

references to the concept of "Thinking" or reflecting

prompts that encourage reflection or consideration

No Comments

No Known Activations