INDEX

Explanations

law enforcement and emergency response-related terms

oai_token-act-pair · gpt-3.5-turbo

references to law enforcement and military presence

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

ãĤ¦ãĤ¹

-0.88

maxwell

-0.80

peat

-0.74

ulent

-0.73

notice

-0.70

stories

-0.68

Does

-0.68

DERR

-0.67

osterone

-0.66

 gratification

-0.66

POSITIVE LOGITS

 helicop

1.22

 escorted

1.18

 battled

1.17

 patrolling

1.15

 conver

1.13

 stationed

1.10

 raided

1.08

 arrived

1.08

 descended

1.07

 comb

1.07

Activations Density 0.203%

law enforcement and emergency response-related terms

references to law enforcement and military presence

No Comments

No Known Activations