INDEX

Explanations

phrases related to serving in roles or positions

oai_token-act-pair · gpt-3.5-turbo

the word "serve" in various 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

ebted

-0.71

bish

-0.71

Scope

-0.65

anta

-0.64

 millenn

-0.63

 Rebell

-0.63

ulous

-0.61

 VIDEOS

-0.60

ModLoader

-0.60

edia

-0.59

POSITIVE LOGITS

ework

0.68

 representing

0.68

strument

0.67

 reserv

0.67

 follows

0.67

 interim

0.66

 afore

0.66

 medi

0.66

abet

0.64

an

0.64

Activations Density 0.038%

phrases related to serving in roles or positions

the word "serve" in various contexts

No Comments

No Known Activations