INDEX

Explanations

percentage and quantitative increases

oai_token-act-pair · gpt-3.5-turbo

terms related to growth or increase 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

PAR

-0.67

 Cabin

-0.65

Images

-0.64

 Stores

-0.62

JECT

-0.61

english

-0.60

rome

-0.59

Ns

-0.59

 Bowman

-0.59

Featured

-0.58

POSITIVE LOGITS

xual

1.19

emaker

0.81

ahead

0.81

backs

0.81

 subsequ

0.80

 stemming

0.79

itures

0.77

ursion

0.76

jriwal

0.76

eful

0.76

Activations Density 0.091%

percentage and quantitative increases

terms related to growth or increase in various contexts

No Comments

No Known Activations