INDEX

Explanations

words or phrases related to activating or triggering events or actions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "trigger"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 endeav

-0.72

inis

-0.69

lot

-0.68

images

-0.68

lik

-0.68

 Caldwell

-0.68

uo

-0.66

iom

-0.65

aqu

-0.64

glas

-0.64

POSITIVE LOGITS

 trigger

3.73

trigger

2.88

 triggers

2.79

 Trigger

2.66

Trigger

2.39

 triggering

2.37

 triggered

1.88

 provoke

1.35

 activate

1.26

 catalyst

1.20

Activations Density 0.017%

words or phrases related to activating or triggering events or actions

occurrences of the word "trigger"

No Comments

No Known Activations