INDEX

Explanations

words related to proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

specific names and references to individuals and characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Mehran

-0.90

 Lancet

-0.69

actionDate

-0.64

 Seym

-0.63

remote

-0.62

zens

-0.59

 Olympus

-0.59

 permanent

-0.59

drivers

-0.59

binding

-0.58

POSITIVE LOGITS

 laughs

1.34

 laughed

1.23

 disagrees

1.22

 replies

1.21

 replied

1.21

 responds

1.20

 chuckled

1.17

 asks

1.15

 smiles

1.12

 agrees

1.12

Activations Density 0.438%

words related to proper nouns or names

specific names and references to individuals and characters

No Comments

No Known Activations