INDEX

Explanations

Roman numerals

oai_token-act-pair · gpt-3.5-turbo

instances of the letters "i" in various sequences

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

boards

-0.74

lins

-0.70

lain

-0.68

light

-0.67

rant

-0.67

insula

-0.65

orie

-0.65

lights

-0.64

meyer

-0.64

ride

-0.62

POSITIVE LOGITS

iii

1.03

ii

0.95

Ã±

0.84

ye

0.77

ppe

0.73

yah

0.73

wi

0.72

ya

0.71

iking

0.71

iting

0.71

Activations Density 0.023%

Roman numerals

instances of the letters "i" in various sequences

No Comments

No Known Activations