INDEX

Explanations

locations or places

oai_token-act-pair · gpt-3.5-turbo

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

 thereafter

-0.72

 afterward

-0.71

 UNCLASSIFIED

-0.67

}.

-0.65

[*

-0.65

.).

-0.62

 afterwards

-0.60

_.

-0.58

selves

-0.58

 beforehand

-0.58

POSITIVE LOGITS

 Brewing

0.69

reetings

0.65

 Calculator

0.64

 âĢº

0.61

Arcade

0.60

 Belfast

0.59

 Podcast

0.59

 Album

0.59

Coin

0.58

Disk

0.55

Activations Density 0.962%

locations or places

No Comments

No Known Activations