INDEX

Explanations

phrase or words related to alerts or notifications

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "alert" and its variations

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

atan

-0.75

 Ogre

-0.73

 Jinn

-0.70

Plex

-0.67

Cube

-0.66

Untitled

-0.65

Pain

-0.63

-0.62

ABE

-0.62

VEN

-0.61

POSITIVE LOGITS

 alert

1.03

ness

0.89

gency

0.88

ingly

0.85

 alerts

0.82

ibility

0.79

aline

0.78

alert

0.76

ilogy

0.76

 Alert

0.75

Activations Density 0.014%

phrase or words related to alerts or notifications

occurrences of the word "alert" and its variations

No Comments

No Known Activations