INDEX

Explanations

words related to causing disturbance or interruption in various contexts

oai_token-act-pair · gpt-3.5-turbo

terms related to disruption or interference in various contexts

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

rera

-0.77

phans

-0.68

ramid

-0.65

puted

-0.65

BuyableInstoreAndOnline

-0.63

True

-0.63

eah

-0.63

aternity

-0.62

hl

-0.61

uct

-0.61

POSITIVE LOGITS

 disrupt

1.11

 havoc

1.00

 disruptive

0.99

 disruptions

0.98

alore

0.96

 disrupting

0.96

 disrupted

0.96

 disruption

0.95

iversal

0.77

 interruption

0.76

Activations Density 0.014%

words related to causing disturbance or interruption in various contexts

terms related to disruption or interference in various contexts

No Comments

No Known Activations