INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

specific names, terms, or identifiers related to data or entities

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

soDeliveryDate

-0.84

Rw

-0.79

 hairst

-0.75

 Guatem

-0.74

 whiff

-0.74

FW

-0.73

wr

-0.73

 Hobby

-0.72

 pupp

-0.71

 jack

-0.71

POSITIVE LOGITS

INE

1.32

ine

1.32

ines

1.19

ined

1.03

idine

1.01

oline

0.97

olate

0.94

amine

0.94

ining

0.94

cius

0.89

Activations Density 0.312%

proper nouns or names

specific names, terms, or identifiers related to data or entities

No Comments

No Known Activations