INDEX

Explanations

words related to categorizing or classifying

oai_token-act-pair · gpt-3.5-turbo

terms related to categorization and classification processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

vous

-0.76

rentice

-0.74

perty

-0.73

 homeland

-0.72

ful

-0.72

noon

-0.72

elin

-0.71

ful

-0.70

vind

-0.68

aukee

-0.67

POSITIVE LOGITS

ifications

0.87

enance

0.87

 classify

0.84

anguage

0.83

encies

0.83

 categor

0.82

ategor

0.82

ically

0.81

ifiers

0.80

 Classification

0.78

Activations Density 0.043%

words related to categorizing or classifying

terms related to categorization and classification processes

No Comments

No Known Activations