INDEX

Explanations

unusual characters within text

oai_token-act-pair · gpt-3.5-turbo

specific characters or symbols present in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

olphin

-0.75

ioned

-0.72

WARD

-0.70

 chilling

-0.68

ifference

-0.68

wards

-0.64

ensitive

-0.64

walk

-0.64

rained

-0.63

ITNESS

-0.63

POSITIVE LOGITS

È

1.26

³

1.17

Ļ

1.09

Ľ

1.07

ł

1.02

ĺ

0.98

½

0.94

£

0.94

Ķ

0.91

ħ

0.91

Activations Density 0.006%

unusual characters within text

specific characters or symbols present in the text

No Comments

No Known Activations