INDEX

Explanations

names or terms related to specific individuals or entities

oai_token-act-pair · gpt-3.5-turbo

words related to specific types of foods or ingredients

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

ionic

-0.81

ancial

-0.78

etheless

-0.77

nesota

-0.71

 simultane

-0.68

INGTON

-0.68

ammy

-0.68

igration

-0.67

neapolis

-0.66

ãĤ¢ãĥ«

-0.66

POSITIVE LOGITS

lli

1.13

llo

1.09

0.96

lla

0.92

tsky

0.91

Ã±o

0.88

vich

0.86

ll

0.85

gg

0.85

lled

0.85

Activations Density 0.169%

names or terms related to specific individuals or entities

words related to specific types of foods or ingredients

No Comments

No Known Activations