INDEX

Explanations

mentions of interviews and discussions related to media content

oai_token-act-pair · gpt-3.5-turbo

segments of conversation or discussion regarding filmmaking and interviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 wrongly

-0.76

vernment

-0.74

":"/

-0.73

 denies

-0.73

wagen

-0.70

 Photograph

-0.69

['

-0.69

iage

-0.69

jet

-0.69

gio

-0.67

POSITIVE LOGITS

Episode

1.07

podcast

1.03

 Episode

1.00

 Podcast

0.99

 LIVE

0.99

CAST

0.92

 podcast

0.89

Guest

0.88

estern

0.88

âķĲ

0.88

Activations Density 0.473%

mentions of interviews and discussions related to media content

segments of conversation or discussion regarding filmmaking and interviews

No Comments

No Known Activations