INDEX

Explanations

words related to written communication and literature

oai_token-act-pair · gpt-3.5-turbo

words related to various types of written works or narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Ì¶

-0.71

ãĥ¼ãĥĨ

-0.66

gypt

-0.66

inelli

-0.63

 withstand

-0.62

issors

-0.60

inki

-0.60

 sterling

-0.59

ãĥ¼ãĥĨãĤ£

-0.59

visor

-0.58

POSITIVE LOGITS

urnal

1.03

hawk

0.82

agon

0.78

xious

0.78

 Chomsky

0.71

onyms

0.69

Reply

0.65

heim

0.64

peak

0.64

 Gallagher

0.63

Activations Density 0.050%

words related to written communication and literature

words related to various types of written works or narratives

No Comments

No Known Activations