INDEX

Explanations

combinations of letters that repeat or are near each other

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to small, intricate details or elements

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

Demand

-0.72

orescence

-0.72

xual

-0.70

Accessory

-0.69

 Awakening

-0.69

IUM

-0.68

Asia

-0.67

ources

-0.65

rio

-0.64

ORTS

-0.64

POSITIVE LOGITS

bour

1.01

jee

0.79

 gritty

0.75

minimum

0.68

pants

0.67

 tumble

0.67

 flour

0.66

pie

0.64

fit

0.61

 bisc

0.61

Activations Density 0.097%

combinations of letters that repeat or are near each other

words and phrases related to small, intricate details or elements

No Comments

No Known Activations