INDEX

Explanations

lines related to political campaigns or regulations

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

concepts related to gaps, boundaries, and distinctions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

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

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_post

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

OUP

-0.92

luck

-0.84

cia

-0.81

peat

-0.77

rpm

-0.76

è¦ļéĨĴ

-0.72

SpaceEngineers

-0.71

STAR

-0.70

ivals

-0.69

ributes

-0.68

POSITIVE LOGITS

 blurred

1.44

 narrowing

1.31

 blurry

1.31

 separating

1.27

 deline

1.26

 widening

1.25

 brid

1.22

 widened

1.20

 porous

1.20

 dividing

1.15

Activations Density 0.357%

lines related to political campaigns or regulations

concepts related to gaps, boundaries, and distinctions in various contexts

No Comments

No Known Activations