INDEX

Explanations

phrases related to pathways or methods

oai_token-act-pair · gpt-3.5-turbo

mentions of methods or manners of doing something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

uster

-0.77

usters

-0.75

encer

-0.68

incinn

-0.67

icio

-0.67

oak

-0.63

asts

-0.62

Ä±

-0.60

grave

-0.60

iosyncr

-0.60

POSITIVE LOGITS

fare

1.03

finding

0.92

point

0.90

WAY

0.82

ward

0.81

aterasu

0.76

forward

0.76

bill

0.72

points

0.71

 Judaism

0.71

Activations Density 0.048%

phrases related to pathways or methods

mentions of methods or manners of doing something

No Comments

No Known Activations