INDEX

Explanations

words related to physical structures or locations

oai_token-act-pair · gpt-3.5-turbo

words pertaining to social dynamics and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Rabbit

-0.74

çĭ

-0.69

PH

-0.67

è£ħ

-0.64

stellar

-0.64

 Bohem

-0.64

 transitional

-0.63

 Trin

-0.63

 Human

-0.63

 Chel

-0.62

POSITIVE LOGITS

acters

1.03

oldown

0.95

akery

0.93

ilities

0.92

ards

0.90

ourse

0.90

aunts

0.88

usters

0.88

ourses

0.88

essing

0.87

Activations Density 0.093%

words related to physical structures or locations

words pertaining to social dynamics and interactions

No Comments

No Known Activations