INDEX

Explanations

proper nouns related to various organizations and locations

oai_token-act-pair · gpt-3.5-turbo

names of organizations, institutions, and companies

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

$.

-0.78

 includ

-0.70

...]

-0.70

 thereof

-0.69

 liking

-0.68

Ò

-0.67

>.

-0.64

perature

-0.63

bec

-0.63

 thats

-0.63

POSITIVE LOGITS

 spokesman

1.02

 spokeswoman

1.01

Ltd

0.94

 spokesperson

0.91

 Solutions

0.84

 Association

0.80

 Corp

0.79

 Holdings

0.78

 Employees

0.77

 Managing

0.77

Activations Density 0.382%

proper nouns related to various organizations and locations

names of organizations, institutions, and companies

No Comments

No Known Activations