INDEX

Explanations

names of specific entities such as cities, places, people and categories

oai_token-act-pair · gpt-3.5-turbo

key entities and concepts related to legal cases and their implications

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

joice

-0.73

dx

-0.69

CAST

-0.68

interrupted

-0.68

thumbnails

-0.67

Pry

-0.67

 condem

-0.64

wards

-0.64

rys

-0.63

repeat

-0.63

POSITIVE LOGITS

é¾įå¥ĳå£«

0.78

 alone

0.75

ieri

0.72

eto

0.68

ativity

0.67

 Cooke

0.66

igmat

0.66

ema

0.61

ISO

0.61

 Ronaldo

0.61

Activations Density 0.200%

names of specific entities such as cities, places, people and categories

key entities and concepts related to legal cases and their implications

No Comments

No Known Activations