INDEX

Explanations

verbs related to physical actions involving some form of throwing or launching

oai_token-act-pair · gpt-3.5-turbo

words and phrases associated with throwing or launching objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ãĥİ

-0.97

Appearance

-0.78

Limited

-0.77

 Borders

-0.72

Availability

-0.71

Balt

-0.71

MAT

-0.64

Few

-0.63

 Differences

-0.63

Modern

-0.62

POSITIVE LOGITS

 projectiles

0.97

 takedown

0.92

 volley

0.92

 cannon

0.88

 punches

0.86

 cannons

0.86

 onto

0.86

 grenades

0.85

 darts

0.85

 bolts

0.84

Activations Density 0.098%

verbs related to physical actions involving some form of throwing or launching

words and phrases associated with throwing or launching objects

No Comments

No Known Activations