INDEX

Explanations

words related to courage

oai_token-act-pair · gpt-3.5-turbo

references to bravery and courage

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

eor

-0.87

payer

-0.75

washer

-0.67

ramid

-0.65

 Noon

-0.65

hemat

-0.64

amac

-0.63

eren

-0.63

Bye

-0.63

oval

-0.61

POSITIVE LOGITS

ously

1.43

 courage

0.92

ous

0.88

isma

0.81

FUL

0.80

 inspiring

0.79

uously

0.76

 Courage

0.75

 bravery

0.75

uous

0.74

Activations Density 0.017%

words related to courage

references to bravery and courage

No Comments

No Known Activations