INDEX

Explanations

questions starting with "What if"

oai_token-act-pair · gpt-3.5-turbo

instances of hypothetical scenarios or conditional statements

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

Eye

-0.67

abre

-0.66

ila

-0.64

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

-0.64

hands

-0.63

akia

-0.63

gae

-0.62

horse

-0.62

arm

-0.61

 depths

-0.60

POSITIVE LOGITS

 someday

0.84

you

0.80

fy

0.75

 they

0.74

 somebody

0.73

 someone

0.72

?]

0.70

we

0.69

 Gutenberg

0.68

 hypot

0.67

Activations Density 0.030%

questions starting with "What if"

instances of hypothetical scenarios or conditional statements

No Comments

No Known Activations