INDEX

Explanations

questions or phrases expressing a need for clarification or definition

oai_token-act-pair · gpt-3.5-turbo

the phrase "what exactly" used 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

por

-0.69

ULTS

-0.68

visors

-0.67

puter

-0.66

ĸļ

-0.66

ker

-0.64

gi

-0.63

tein

-0.63

lyn

-0.63

aily

-0.62

POSITIVE LOGITS

 transpired

1.03

 constitutes

0.85

 happened

0.80

 qualifies

0.79

 Exactly

0.75

 distinguishes

0.75

 differs

0.75

 happens

0.72

 separates

0.72

ifications

0.71

Activations Density 0.026%

questions or phrases expressing a need for clarification or definition

the phrase "what exactly" used in various contexts

No Comments

No Known Activations