INDEX

Explanations

words related to causing or being affected by disturbances or interruptions

oai_token-act-pair · gpt-3.5-turbo

mentions of disruption and its impact on various contexts and entities

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

IFrame

Link

Negative Logits

rera

-0.77

eah

-0.71

ramid

-0.67

phans

-0.67

gas

-0.65

gom

-0.65

uct

-0.64

mber

-0.63

hl

-0.63

geries

-0.62

POSITIVE LOGITS

 disrupt

1.04

 disrupted

0.95

 disruptions

0.94

 disrupting

0.93

 disruptive

0.93

 disruption

0.91

alore

0.90

 havoc

0.89

iversal

0.74

ively

0.73

Activations Density 0.020%

words related to causing or being affected by disturbances or interruptions

mentions of disruption and its impact on various contexts and entities

No Known Activations