INDEX

Explanations

hypothetical scenarios or questions beginning with "What if"

oai_token-act-pair · gpt-3.5-turbo

the phrase "What if" indicating hypothetical scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

avor

-0.70

GMT

-0.67

Mech

-0.66

%);

-0.65

ãĥ´

-0.63

ãĥ¡

-0.63

 depths

-0.62

ãĥĥ

-0.61

wash

-0.59

aucuses

-0.59

POSITIVE LOGITS

yip

0.92

fy

0.86

you

0.76

rame

0.76

ihad

0.73

soever

0.73

yon

0.70

 they

0.69

 thou

0.67

llor

0.66

Activations Density 0.038%

hypothetical scenarios or questions beginning with "What if"

the phrase "What if" indicating hypothetical scenarios

No Comments

No Known Activations