INDEX

Explanations

phrases starting with "While"

oai_token-act-pair · gpt-3.5-turbo

the word "While" indicating contrasting or contextual relationships in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ISE

-0.79

cause

-0.79

dayName

-0.79

SPONSORED

-0.77

tnc

-0.73

_-_

-0.73

DragonMagazine

-0.72

pmwiki

-0.71

itud

-0.70

IZE

-0.69

POSITIVE LOGITS

 acknowledging

1.25

 researching

1.07

 conced

0.99

 admittedly

0.96

 discussing

0.94

 technically

0.93

 there

0.92

 many

0.90

 maintaining

0.90

 admitting

0.90

Activations Density 0.083%

phrases starting with "While"

the word "While" indicating contrasting or contextual relationships in statements

No Comments

No Known Activations