INDEX

Explanations

phrases related to modes and policies

oai_token-act-pair · gpt-3.5-turbo

context related to theatre and performance modes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 perspect

-0.63

 dots

-0.61

 tremend

-0.60

ŃĶ

-0.58

 ultras

-0.58

legged

-0.58

soDeliveryDate

-0.58

chall

-0.56

ties

-0.56

 knot

-0.55

POSITIVE LOGITS

↵

0.70

<|endoftext|>

0.68

 Thumbnails

0.66

 ..........

0.63

 Loading

0.63

VERTISEMENT

0.63

 Reese

0.62

Developer

0.61

 Advertisement

0.61

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

0.61

Activations Density 0.034%

phrases related to modes and policies

context related to theatre and performance modes

No Comments

No Known Activations