INDEX

Explanations

phrases related to computer programming languages and concepts, such as variable names, code snippets, and programming rules

oai_token-act-pair · gpt-3.5-turbo

statements of importance or significance in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Cele

-0.71

 patriotic

-0.64

eligible

-0.63

ocaust

-0.62

 stricken

-0.60

Hours

-0.60

 disgr

-0.59

campaign

-0.59

 nationally

-0.59

 voted

-0.58

POSITIVE LOGITS

 theorem

1.22

 diagram

1.18

 analogy

1.17

 algebra

1.06

 intuition

1.05

 diagrams

1.05

 simplified

1.03

 simpl

1.03

 Suppose

1.02

 simplify

1.02

Activations Density 0.866%

phrases related to computer programming languages and concepts, such as variable names, code snippets, and programming rules

statements of importance or significance in various contexts

No Comments

No Known Activations