INDEX

Explanations

mentions of categories or groups within society

oai_token-act-pair · gpt-3.5-turbo

terms related to various groups and categories of people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Reloaded

-0.75

OLOG

-0.67

saf

-0.67

rawdownloadcloneembedreportprint

-0.65

ASED

-0.63

ilogy

-0.62

GoldMagikarp

-0.60

oÄŁ

-0.59

 charm

-0.59

 pestic

-0.58

POSITIVE LOGITS

hips

1.15

paces

1.13

 alike

1.13

hip

1.11

pace

0.98

hops

0.82

chool

0.82

ets

0.80

0.77

ervatives

0.75

Activations Density 0.456%

mentions of categories or groups within society

terms related to various groups and categories of people

No Comments

No Known Activations