INDEX

Explanations

descriptions inviting the viewer to explore more detailed information

oai_token-act-pair · gpt-3.5-turbo

phrases related to in-depth analysis or detailed explanations

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

ãĥĲ

-0.75

ylum

-0.64

iously

-0.63

bugs

-0.62

 Canaver

-0.62

 committees

-0.62

rug

-0.61

 gamb

-0.59

 SHALL

-0.59

 shroud

-0.59

POSITIVE LOGITS

ottest

0.80

 details

0.73

 enlarg

0.70

 info

0.70

 highlights

0.70

 CLICK

0.69

arger

0.69

 FREE

0.69

 Gloss

0.68

 LINK

0.67

Activations Density 0.368%

descriptions inviting the viewer to explore more detailed information

phrases related to in-depth analysis or detailed explanations

No Comments

No Known Activations