INDEX

Explanations

specific mentions of the word "directly" in the text

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "directly."

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

gerald

-0.82

glers

-0.79

 Garry

-0.73

 Daily

-0.68

 Scor

-0.66

 Boys

-0.66

 Kirin

-0.66

 Millennium

-0.66

 Killer

-0.65

ulton

-0.65

POSITIVE LOGITS

 contradicted

0.91

 identifiable

0.86

 contradicts

0.81

 contradict

0.80

 benefited

0.76

cedented

0.75

 direct

0.71

 addressed

0.71

 attributable

0.71

 confront

0.70

Activations Density 0.017%

specific mentions of the word "directly" in the text

occurrences of the word "directly."

No Comments

No Known Activations