INDEX

Explanations

proper nouns like names of people and places

oai_token-act-pair · gpt-3.5-turbo

names of locations, people, and references to specific entities

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

 offseason

-0.57

 kidding

-0.57

iaries

-0.55

 minority

-0.55

,''

-0.55

 refer

-0.55

 worthwhile

-0.54

 trigger

-0.53

 appre

-0.53

PID

-0.53

POSITIVE LOGITS

itto

0.80

eln

0.69

tein

0.68

enture

0.67

[(

0.66

endez

0.66

ombies

0.66

vic

0.65

anooga

0.65

emetery

0.65

Activations Density 0.472%

proper nouns like names of people and places

names of locations, people, and references to specific entities

No Comments

No Known Activations