INDEX

Explanations

words ending in 'ed'

oai_token-act-pair · gpt-3.5-turbo

past participles

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¥³

-0.85

è£ħ

-0.77

 Leilan

-0.69

ufact

-0.68

å£

-0.67

avez

-0.65

clud

-0.64

ORY

-0.64

SPONSORED

-0.61

perty

-0.61

POSITIVE LOGITS

nesday

0.95

uct

0.87

ict

0.87

dit

0.85

rive

0.84

uled

0.83

ges

0.82

ging

0.80

monton

0.77

hog

0.76

Activations Density 0.064%

words ending in 'ed'

past participles

No Comments

No Known Activations