INDEX

Explanations

conditional statements starting with 'if'

oai_token-act-pair · gpt-3.5-turbo

conditional statements using the word "if"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

-0.86

ãĤª

-0.74

Rated

-0.72

FTWARE

-0.70

STAR

-0.68

%);

-0.67

ATIONAL

-0.66

ORPG

-0.66

 Nationwide

-0.64

ãĤ¨ãĥ«

-0.62

POSITIVE LOGITS

soever

1.01

fy

0.97

rame

0.90

you

0.84

uana

0.83

yip

0.82

 they

0.78

 unchecked

0.76

 necessary

0.74

 anything

0.74

Activations Density 0.107%

conditional statements starting with 'if'

conditional statements using the word "if"

No Comments

No Known Activations