INDEX

Explanations

proper nouns related to military or combat terminology, such as "saber" and "Fang."

oai_token-act-pair · gpt-3.5-turbo

references to 'saber' and other related terminology 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

McA

-0.96

oke

-0.81

uters

-0.74

 Dover

-0.73

icut

-0.72

essa

-0.72

 Airlines

-0.70

ipop

-0.69

 Pharma

-0.68

Osc

-0.67

POSITIVE LOGITS

sab

0.89

ystem

0.84

 guiActiveUn

0.81

lasses

0.79

emen

0.78

raph

0.77

ses

0.76

xual

0.76

 glim

0.73

pread

0.71

Activations Density 0.019%

proper nouns related to military or combat terminology, such as "saber" and "Fang."

references to 'saber' and other related terminology in various contexts

No Known Activations