INDEX

Explanations

words related to alarms

oai_token-act-pair · gpt-3.5-turbo

references to various forms of alarms or alerts

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

lease

-0.78

merga

-0.73

tein

-0.69

arnaev

-0.69

forms

-0.68

buff

-0.68

employment

-0.65

©¶æ

-0.64

gru

-0.64

 snipp

-0.64

POSITIVE LOGITS

ingly

1.10

 bells

1.07

ously

0.97

clock

0.91

Clock

0.88

 Clock

0.87

 alarm

0.87

 clock

0.87

 clocks

0.79

bell

0.77

Activations Density 0.019%

words related to alarms

references to various forms of alarms or alerts

No Comments

No Known Activations