INDEX

Explanations

references to the term "Trotsky" or variations thereof

oai_token-act-pair · gpt-3.5-turbo

references to military or law enforcement personnel and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ually

-0.69

UAL

-0.69

 Reloaded

-0.67

ãĤ¦ãĤ¹

-0.62

alam

-0.62

ividual

-0.61

++++++++++++++++

-0.60

arians

-0.58

arten

-0.58

ilated

-0.57

POSITIVE LOGITS

dden

1.17

opers

1.15

phies

1.11

ppo

1.09

opa

0.98

pez

0.96

plets

0.93

phy

0.93

tted

0.92

jan

0.91

Activations Density 0.030%

references to the term "Trotsky" or variations thereof

references to military or law enforcement personnel and entities

No Comments

No Known Activations