INDEX

Explanations

questions starting with "Which" followed by a verb

oai_token-act-pair · gpt-3.5-turbo

the word "which" indicating questions or clarifications

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Gy

-0.68

Bas

-0.68

Rog

-0.67

gy

-0.67

GROUND

-0.65

bug

-0.65

GY

-0.64

mob

-0.64

Bo

-0.63

BLE

-0.62

POSITIVE LOGITS

soever

0.88

 brings

0.82

 surprises

0.76

xual

0.75

ãĥ¯ãĥ³

0.74

 begs

0.72

espie

0.68

 contrasts

0.64

Ã±o

0.63

eele

0.63

Activations Density 0.085%

questions starting with "Which" followed by a verb

the word "which" indicating questions or clarifications

No Comments

No Known Activations