INDEX

Explanations

references to locations in the United States

oai_token-act-pair · gpt-3.5-turbo

references to the United States

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

struct

-0.63

 penet

-0.63

param

-0.60

iosyn

-0.59

ioned

-0.59

Dog

-0.57

 incorpor

-0.57

ĪĴ

-0.56

 Puppet

-0.56

 branching

-0.56

POSITIVE LOGITS

 Indies

0.86

 Isles

0.83

vale

0.82

 Territories

0.81

 illegally

0.80

ADA

0.79

liga

0.77

outheastern

0.74

ICAN

0.71

au

0.69

Activations Density 0.120%

references to locations in the United States

references to the United States

No Comments

No Known Activations