INDEX

Explanations

words related to exploration or expeditions

oai_token-act-pair · gpt-3.5-turbo

words related to expeditions and exploration

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

colo

-0.86

corn

-0.86

creen

-0.82

cher

-0.70

lined

-0.69

 basil

-0.67

Klu

-0.65

gage

-0.65

ched

-0.64

practice

-0.62

POSITIVE LOGITS

 expedition

1.18

 Expedition

1.14

ary

0.98

 Everest

0.97

ogue

0.93

arily

0.91

voy

0.89

 explorer

0.86

 exped

0.86

 Explorer

0.84

Activations Density 0.030%

words related to exploration or expeditions

words related to expeditions and exploration

No Comments

No Known Activations