INDEX

Explanations

words related to locations or events associated with major incidents or crises

oai_token-act-pair · gpt-3.5-turbo

references to significant events and locations related to violence and conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 acron

-0.76

ãĥ³ãĤ¸

-0.68

minist

-0.65

 abbre

-0.65

Standard

-0.64

SHIP

-0.63

Companies

-0.62

elist

-0.61

adv

-0.61

onite

-0.61

POSITIVE LOGITS

 perpetrated

0.91

 ignited

0.88

 sparked

0.83

 provoked

0.82

ascus

0.82

 escalated

0.81

 detonated

0.77

 caused

0.76

 outwe

0.76

 spurred

0.75

Activations Density 0.279%

words related to locations or events associated with major incidents or crises

references to significant events and locations related to violence and conflict

No Comments

No Known Activations