INDEX

Explanations

locations within a software development environment

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in" within various contexts

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

ens

-0.75

CLASSIFIED

-0.74

HAEL

-0.74

 contag

-0.70

hur

-0.67

 lett

-0.66

 staffers

-0.65

llor

-0.64

ļ

-0.63

 whistleblowers

-0.63

POSITIVE LOGITS

 lieu

1.34

 accordance

1.29

 conjunction

1.26

animate

1.17

 addition

1.17

ordinate

1.12

clusions

1.10

 order

1.09

clusively

1.08

 relation

1.07

Activations Density 0.366%

locations within a software development environment

occurrences of the word "in" within various contexts

No Comments

No Known Activations