INDEX

Explanations

words related to conflicts, specifically civil wars

oai_token-act-pair · gpt-3.5-turbo

references to ongoing conflicts and wars

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

umbn

-0.71

bnb

-0.70

 infinity

-0.68

ECD

-0.66

Chance

-0.65

asonic

-0.62

 Transactions

-0.62

 Tennis

-0.62

 Gifts

-0.61

MET

-0.60

POSITIVE LOGITS

 raged

1.17

 raging

1.16

torn

1.12

lords

1.04

 ravaged

0.99

 flared

0.97

 erupted

0.96

lord

0.94

 engulf

0.93

 plag

0.90

Activations Density 0.117%

words related to conflicts, specifically civil wars

references to ongoing conflicts and wars

No Comments

No Known Activations