INDEX

Explanations

words with special characters, potentially indicating names or titles

oai_token-act-pair · gpt-3.5-turbo

occurrences of special characters or symbols

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

 scatter

-0.77

 scattering

-0.74

Roc

-0.73

 FISA

-0.70

 Saga

-0.70

 DRAG

-0.67

 Dirt

-0.67

 Farming

-0.65

osate

-0.65

 whirlwind

-0.62

POSITIVE LOGITS

º

1.12

¹

1.06

į

1.01

»

1.00

£

0.98

½

0.93

¼

0.88

¡

0.87

ake

0.87

²

0.86

Activations Density 0.471%

words with special characters, potentially indicating names or titles

occurrences of special characters or symbols

No Comments

No Known Activations