INDEX

Explanations

mentions of "mini-" followed by a variety of words and phrases

oai_token-act-pair · gpt-3.5-turbo

references to small or miniature concepts

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

âķĲâķĲ

-0.78

Ö¼

-0.77

xual

-0.73

rer

-0.67

ILLE

-0.66

ï¸

-0.66

 Directorate

-0.64

rir

-0.63

KI

-0.63

lain

-0.62

POSITIVE LOGITS

ature

1.39

atur

1.32

atures

1.08

ocular

0.87

ota

0.86

atomic

0.78

 sized

0.77

oby

0.75

eco

0.74

ogo

0.74

Activations Density 0.017%

mentions of "mini-" followed by a variety of words and phrases

references to small or miniature concepts

No Comments

No Known Activations