INDEX

Explanations

the word "term"

oai_token-act-pair · gpt-3.5-turbo

the concept of "term" as it relates to definitions or classifications

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

ierrez

-0.74

âĹ¼

-0.73

©¶æ¥µ

-0.71

¥ŀ

-0.70

hs

-0.67

artney

-0.67

NetMessage

-0.64

 Depths

-0.64

 Federation

-0.63

 istg

-0.62

POSITIVE LOGITS

icide

0.94

ifier

0.92

marks

0.86

 coined

0.85

icides

0.80

mark

0.77

ology

0.76

sworth

0.74

ifiers

0.74

marine

0.74

Activations Density 0.024%

the word "term"

the concept of "term" as it relates to definitions or classifications

No Comments

No Known Activations