INDEX

Explanations

quantifiers like "even"

oai_token-act-pair · gpt-3.5-turbo

the word "even" and its contextual variations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aim

-0.81

idelines

-0.72

ursed

-0.69

ffen

-0.68

ributes

-0.67

IGHT

-0.67

plex

-0.65

ample

-0.65

isen

-0.64

rend

-0.64

POSITIVE LOGITS

 remotely

1.09

 outright

0.77

romeda

0.72

tho

0.70

 stranger

0.70

 worse

0.70

 though

0.67

nam

0.67

 moderately

0.63

este

0.62

Activations Density 0.027%

quantifiers like "even"

the word "even" and its contextual variations

No Comments

No Known Activations