INDEX

Explanations

lists of items like shirts, memes, and illustrations mentioned in various contexts

oai_token-act-pair · gpt-3.5-turbo

lists of items or elements in a contextual framework

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ishment

-0.69

ONSORED

-0.68

aste

-0.64

¬¼

-0.62

lord

-0.61

itus

-0.59

ail

-0.58

iness

-0.57

emaker

-0.57

 itself

-0.57

POSITIVE LOGITS

etc

1.13

 respectively

1.05

 including

1.03

etc

1.02

Downloadha

0.99

 albeit

0.90

 namely

0.90

including

0.86

 Flavoring

0.86

 Including

0.84

Activations Density 0.509%

lists of items like shirts, memes, and illustrations mentioned in various contexts

lists of items or elements in a contextual framework

No Comments

No Known Activations