INDEX

Explanations

references to a specific location, in this case, Utah

oai_token-act-pair · gpt-3.5-turbo

references to the state of Utah

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

hops

-0.74

lihood

-0.74

enegger

-0.72

mercial

-0.66

alez

-0.65

schild

-0.63

Word

-0.63

unct

-0.63

 depreciation

-0.63

emis

-0.63

POSITIVE LOGITS

Utah

1.12

 Utah

1.02

 Jazz

1.01

 Rapids

0.92

ns

0.85

 Territory

0.79

 Valley

0.76

 Salt

0.76

 Mormons

0.75

 Idaho

0.74

Activations Density 0.005%

references to a specific location, in this case, Utah

references to the state of Utah

No Comments

No Known Activations