INDEX

Explanations

mentions of the word "Dodge"

oai_token-act-pair · gpt-3.5-turbo

references to the brand "Dodge."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

*/(

-0.78

ISC

-0.71

onyms

-0.68

ispers

-0.65

atics

-0.65

Ħ¢

-0.62

-0.61

 Atmosp

-0.61

 Kafka

-0.60

icrobial

-0.59

POSITIVE LOGITS

ball

1.07

wagon

0.97

rolet

0.93

balls

0.91

odge

0.90

 Dodge

0.88

bike

0.86

 Viper

0.85

 dodge

0.79

bage

0.78

Activations Density 0.015%

mentions of the word "Dodge"

references to the brand "Dodge."

No Comments

No Known Activations