INDEX

Explanations

programming-related terms and commands

oai_token-act-pair · gpt-3.5-turbo

command-like structures or technical terminology in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

llah

-0.78

ploy

-0.65

obe

-0.64

panic

-0.63

stroke

-0.62

pread

-0.61

 Poles

-0.61

Afee

-0.60

º

-0.60

ocy

-0.59

POSITIVE LOGITS

 which

1.00

which

0.96

aka

0.89

 whereby

0.86

 chaired

0.78

iHUD

0.78

 wherein

0.78

 nicknamed

0.76

 spearheaded

0.70

 renamed

0.68

Activations Density 0.664%

programming-related terms and commands

command-like structures or technical terminology in the text

No Comments

No Known Activations