INDEX

Explanations

terms related to direct connections or relationships between various entities

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate direct relationships or connections

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

gerald

-0.94

glers

-0.75

ĸļ

-0.72

ulton

-0.71

ifully

-0.69

 Garry

-0.69

 Password

-0.65

lis

-0.63

 Scor

-0.62

 Daily

-0.62

POSITIVE LOGITS

 contradicted

0.88

 identifiable

0.80

forward

0.79

 contradicts

0.79

 benefited

0.76

ebted

0.74

 impacted

0.74

 addressed

0.73

 contradict

0.72

 attributable

0.71

Activations Density 0.019%

terms related to direct connections or relationships between various entities

phrases that indicate direct relationships or connections

No Comments

No Known Activations