INDEX

Explanations

names of locations or businesses

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'W' in various contexts

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

 unpre

-0.80

 bottleneck

-0.77

 apprehension

-0.73

 gratification

-0.70

 afore

-0.67

İĭ

-0.65

 Prelude

-0.65

arial

-0.63

uate

-0.61

 unrestricted

-0.61

POSITIVE LOGITS

OW

1.28

restling

1.27

ITNESS

1.25

atts

1.25

ITCH

1.20

anted

1.18

atson

1.16

alking

1.15

INGS

1.15

ALK

1.13

Activations Density 0.033%

names of locations or businesses

occurrences of the letter 'W' in various contexts

No Comments

No Known Activations