INDEX

Explanations

phrases related to dialogue in narratives

oai_token-act-pair · gpt-3.5-turbo

the occurrence of a specific character or symbol

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 likeness

-0.81

 overloaded

-0.75

 imperson

-0.74

 controvers

-0.73

 resemblance

-0.72

chnology

-0.72

inent

-0.71

 unwanted

-0.71

 unconscious

-0.70

 resemb

-0.70

POSITIVE LOGITS

ï¸ı

1.04

Â¯

1.04

âĶģ

0.89

âĶĢâĶĢâĶĢâĶĢ

0.89

âĻ¦

0.84

ï¸

0.83

Â°

0.83

laughs

0.80

VERTISEMENT

0.80

ef

0.80

Activations Density 0.248%

phrases related to dialogue in narratives

the occurrence of a specific character or symbol

No Comments

No Known Activations