INDEX

Explanations

hypothetical questions using the phrase "What if."

oai_token-act-pair · gpt-3.5-turbo

conditional phrases that prompt hypothetical scenarios

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

omi

-0.72

nect

-0.69

================================================================

-0.69

arm

-0.66

 depths

-0.66

bird

-0.65

WAYS

-0.65

avor

-0.64

horse

-0.64

psey

-0.63

POSITIVE LOGITS

 Gutenberg

0.74

 thou

0.72

you

0.72

 they

0.72

yip

0.70

fy

0.69

 hypot

0.69

 landlords

0.64

 Melania

0.63

we

0.62

Activations Density 0.031%

hypothetical questions using the phrase "What if."

conditional phrases that prompt hypothetical scenarios

No Comments

No Known Activations