INDEX

Explanations

words signaling a positive outcome or solution

oai_token-act-pair · gpt-3.5-turbo

expressions of relief or gratitude

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

gate

-0.71

pled

-0.67

QL

-0.67

angles

-0.62

agg

-0.62

 kindred

-0.61

dq

-0.61

omin

-0.61

utenberg

-0.61

POSITIVE LOGITS

 fortunately

0.93

nown

0.83

terday

0.82

 luckily

0.77

 enough

0.71

 thankfully

0.71

Fortunately

0.70

Thankfully

0.70

ESA

0.69

phans

0.65

Activations Density 0.014%

words signaling a positive outcome or solution

expressions of relief or gratitude

No Comments

No Known Activations