INDEX

Explanations

phrases related to experienced individuals or professionals

oai_token-act-pair · gpt-3.5-turbo

instances of the word "veteran" and its related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

matic

-0.92

laws

-0.89

efficients

-0.87

apo

-0.85

orie

-0.82

rams

-0.78

alter

-0.78

enza

-0.75

ramid

-0.72

mosp

-0.72

POSITIVE LOGITS

 veteran

0.81

 homelessness

0.75

 Veteran

0.73

 veterans

0.73

TAIN

0.68

 adventurer

0.66

 Veterans

0.66

 vets

0.63

 grou

0.62

 widow

0.62

Activations Density 0.017%

phrases related to experienced individuals or professionals

instances of the word "veteran" and its related contexts

No Comments

No Known Activations