INDEX

Explanations

mentions of specific plant-related terms, like plant species or plant parts

oai_token-act-pair · gpt-3.5-turbo

mentions of plants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

deen

-0.83

DOS

-0.77

*/(

-0.75

yip

-0.74

dash

-0.73

alty

-0.72

xes

-0.72

cade

-0.72

cffffcc

-0.69

ROR

-0.69

POSITIVE LOGITS

 plants

1.07

ronics

0.87

 vegetation

0.86

 foliage

0.86

 Plants

0.85

 plant

0.83

 gardens

0.83

 seeds

0.77

 trees

0.76

 flora

0.75

Activations Density 0.025%

mentions of specific plant-related terms, like plant species or plant parts

mentions of plants

No Comments

No Known Activations