INDEX

Explanations

phrases comparing two things, stating that one thing is more like the other

oai_token-act-pair · gpt-3.5-turbo

phrases expressing comparisons or analogies

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

Sharp

-0.75

 Cros

-0.70

 Vacc

-0.69

RAW

-0.69

;;;;;;;;;;;;

-0.68

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.62

©¶æ¥µ

-0.61

Stars

-0.60

phia

-0.60

Arch

-0.60

POSITIVE LOGITS

 than

1.53

than

1.48

 Than

1.12

erous

0.77

oult

0.71

cientious

0.69

rah

0.68

oot

0.68

vention

0.67

ner

0.66

Activations Density 0.152%

phrases comparing two things, stating that one thing is more like the other

phrases expressing comparisons or analogies

No Comments

No Known Activations