INDEX

Explanations

numerical values or quantities

oai_token-act-pair · gpt-3.5-turbo

phrases indicating approximate quantities or estimates

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

chens

-0.81

 Peaks

-0.78

ses

-0.72

Write

-0.68

Express

-0.66

 Shift

-0.65

NEY

-0.65

rift

-0.63

hesis

-0.62

BT

-0.62

POSITIVE LOGITS

 halfway

0.84

PsyNetMessage

0.77

aleb

0.76

 midway

0.75

 Ambro

0.73

pload

0.72

 dozen

0.69

addons

0.67

0.66

0.65

Activations Density 0.075%

numerical values or quantities

phrases indicating approximate quantities or estimates

No Comments

No Known Activations