INDEX

Explanations

words related to conflict or confrontation with an opponent

oai_token-act-pair · gpt-3.5-turbo

mentions of "enemy" 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 @ 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

uesday

-0.79

hetti

-0.78

oled

-0.78

eret

-0.77

ajo

-0.75

atism

-0.75

aughs

-0.74

orrow

-0.72

aza

-0.71

utic

-0.71

POSITIVE LOGITS

 combatants

1.09

 invasion

0.84

 enemy

0.83

 takeover

0.82

 fighters

0.80

 Enemy

0.77

 commander

0.76

 ambush

0.75

 horde

0.75

 soldier

0.74

Activations Density 0.028%

words related to conflict or confrontation with an opponent

mentions of "enemy" in various contexts

No Comments

No Known Activations