INDEX

Explanations

words related to various subcategories or groups

oai_token-act-pair · gpt-3.5-turbo

plural nouns or terms related to various groups or classifications

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

PDATE

-0.72

 condition

-0.67

 practition

-0.66

âĸ¬

-0.65

 exha

-0.61

ļé

-0.61

 conditions

-0.60

hold

-0.59

ufact

-0.59

 circumstances

-0.59

POSITIVE LOGITS

aurus

1.55

hip

1.44

cale

1.27

hips

1.21

ilver

1.20

peed

1.20

paces

1.18

ystem

1.17

kaya

1.16

mith

1.15

Activations Density 0.293%

words related to various subcategories or groups

plural nouns or terms related to various groups or classifications

No Comments

No Known Activations