INDEX

Explanations

interview-related keywords and phrases

oai_token-act-pair · gpt-3.5-turbo

phrases related to interviews or public discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

aceae

-0.71

ãĥīãĥ©

-0.70

Catalog

-0.67

vir

-0.67

_{

-0.63

 notation

-0.63

âĨĳ

-0.62

chrome

-0.62

etsy

-0.61

 broom

-0.60

POSITIVE LOGITS

 MSNBC

1.25

 CNBC

1.20

 interviewer

1.17

 HuffPost

1.13

 interview

1.10

CNN

1.09

 podcast

1.09

ITV

1.08

 Hannity

1.07

 aired

1.05

Activations Density 0.404%

interview-related keywords and phrases

phrases related to interviews or public discussions

No Comments

No Known Activations