INDEX

Explanations

keywords related to enhancements, improvements, or positive additions

oai_token-act-pair · gpt-3.5-turbo

words related to various types of "ments," indicating actions or conditions, such as government and academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

sw

-0.74

\\\\\\\\

-0.71

²¾

-0.68

ãĥ£

-0.64

Reviewer

-0.61

ãĥį

-0.58

lif

-0.58

 bread

-0.58

non

-0.58

 striking

-0.58

POSITIVE LOGITS

poons

1.24

omething

1.18

uits

1.06

mith

1.05

poon

1.05

ilver

1.04

hirt

1.03

peed

1.03

pring

1.00

cape

1.00

Activations Density 0.054%

keywords related to enhancements, improvements, or positive additions

words related to various types of "ments," indicating actions or conditions, such as government and academic contexts

No Comments

No Known Activations