INDEX

Explanations

phrases related to support or endorsement

oai_token-act-pair · gpt-3.5-turbo

references to support or endorsement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

anny

-0.84

odor

-0.72

ities

-0.72

Osc

-0.71

achu

-0.70

tein

-0.70

anooga

-0.70

ogens

-0.69

istics

-0.68

eway

-0.68

POSITIVE LOGITS

 backed

0.89

 backing

0.78

swing

0.77

abies

0.73

backed

0.73

drive

0.70

GROUND

0.69

 arming

0.65

 milit

0.64

lash

0.64

Activations Density 0.013%

phrases related to support or endorsement

references to support or endorsement

No Comments

No Known Activations