INDEX

Explanations

phrases indicating future events or plans

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "be" in various forms and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Bars

-0.67

might

-0.65

 Genius

-0.64

onic

-0.64

usc

-0.63

arming

-0.63

orem

-0.63

 Oops

-0.62

emonic

-0.62

 sickness

-0.61

POSITIVE LOGITS

 able

1.10

 rewarded

1.05

 judged

0.97

fitting

0.95

 replaced

0.93

 remembered

0.93

heading

0.90

 phased

0.90

 subjected

0.89

ige

0.89

Activations Density 0.177%

phrases indicating future events or plans

instances of the verb "be" in various forms and contexts

No Comments

No Known Activations