INDEX

Explanations

topics related to various events or updates within different contexts, such as contests, premiers, guides, news alerts, and more

oai_token-act-pair · gpt-3.5-turbo

terms related to events or changes occurring, particularly in a news or update context

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

perature

-0.83

omever

-0.82

olson

-0.75

 thereof

-0.69

 tide

-0.66

 toget

-0.66

 kingdom

-0.66

å£

-0.65

ardless

-0.63

arching

-0.63

POSITIVE LOGITS

 Manager

0.97

 âĵĺ

0.94

 Profile

0.93

 Releases

0.93

Ltd

0.90

 Ratings

0.90

 Rankings

0.89

 Responsibility

0.85

 Reviews

0.84

 Units

0.83

Activations Density 0.419%

topics related to various events or updates within different contexts, such as contests, premiers, guides, news alerts, and more

terms related to events or changes occurring, particularly in a news or update context

No Comments

No Known Activations