INDEX

Explanations

phrases related to making decisions or taking actions

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, particularly commas

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

ady

-0.67

 Archive

-0.58

ãĤ´ãĥ³

-0.58

ulz

-0.56

é¾

-0.56

izens

-0.55

ulously

-0.55

args

-0.55

rencies

-0.54

urrent

-0.54

POSITIVE LOGITS

 yeah

1.20

 mathemat

0.98

 frankly

0.92

etc

0.91

 blah

0.90

 maybe

0.90

uh

0.90

 whereas

0.87

 basically

0.85

 somebody

0.85

Activations Density 0.381%

phrases related to making decisions or taking actions

punctuation marks, particularly commas

No Comments

No Known Activations