INDEX

Explanations

phrases related to actions or tasks that need to be completed

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate instructions or requirements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

cedented

-0.82

 impacted

-0.71

iture

-0.70

 impaired

-0.68

conservancy

-0.66

 harmed

-0.64

interstitial

-0.63

emy

-0.62

 collided

-0.61

 hardest

-0.60

POSITIVE LOGITS

 click

0.77

 CLICK

0.74

cks

0.70

Submit

0.70

ECK

0.66

rase

0.66

 Fighters

0.66

ickets

0.66

 flick

0.65

ername

0.65

Activations Density 0.106%

phrases related to actions or tasks that need to be completed

phrases that indicate instructions or requirements

No Comments

No Known Activations