INDEX

Explanations

phrases indicating possibility or hypothetical situations

oai_token-act-pair · gpt-3.5-turbo

conditional statements and hypothetical scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Chal

-0.62

è¦ļéĨĴ

-0.62

 Xuan

-0.62

 Scand

-0.57

 Named

-0.56

sho

-0.56

 Moving

-0.55

 Writing

-0.55

 Scor

-0.54

 Nieto

-0.54

POSITIVE LOGITS

 ideally

1.04

be

1.01

 surely

1.00

 doubtless

0.98

 undoubtedly

0.97

 certainly

0.96

 probably

0.95

 require

0.95

 imply

0.94

 suffice

0.93

Activations Density 0.178%

phrases indicating possibility or hypothetical situations

conditional statements and hypothetical scenarios

No Comments

No Known Activations