INDEX

Explanations

terms related to demilitarized zones

oai_token-act-pair · gpt-3.5-turbo

variations of the word "militant" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

swer

-0.79

 Vive

-0.77

shock

-0.71

etheless

-0.69

waves

-0.67

BOOK

-0.65

smanship

-0.64

words

-0.64

stairs

-0.64

nor

-0.63

POSITIVE LOGITS

ament

1.22

arians

1.02

assed

0.95

ician

0.90

udes

0.90

atem

0.88

acion

0.87

arie

0.87

aci

0.85

assing

0.83

Activations Density 0.018%

terms related to demilitarized zones

variations of the word "militant" in different contexts

No Comments

No Known Activations