INDEX

Explanations

phrases related to online articles or content with editorial content, such as blog posts and news articles

oai_token-act-pair · gpt-3.5-turbo

prepositions indicating locations or contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

imony

-0.75

bye

-0.67

ium

-0.66

iameter

-0.66

otype

-0.64

ãĥİ

-0.62

iannopoulos

-0.62

 onwards

-0.62

IQ

-0.62

oscope

-0.61

POSITIVE LOGITS

rolet

0.69

 Albion

0.65

 Pont

0.63

Rab

0.61

phrine

0.60

Il

0.60

hus

0.59

Hung

0.58

 Cerberus

0.58

 Rost

0.57

Activations Density 0.059%

phrases related to online articles or content with editorial content, such as blog posts and news articles

prepositions indicating locations or contexts

No Comments

No Known Activations