INDEX

Explanations

words related to gratitude and appreciation

oai_token-act-pair · gpt-3.5-turbo

linguistic expressions of approval or positivity

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

=]

-0.54

[_

-0.49

glers

-0.46

 droid

-0.45

YP

-0.44

 incent

-0.43

pus

-0.43

](

-0.43

hement

-0.42

itent

-0.42

POSITIVE LOGITS

atche

0.55

Abe

0.49

 Dalai

0.48

ONSORED

0.47

cens

0.46

 Deborah

0.46

appiness

0.45

RESULTS

0.44

UTC

0.44

metic

0.43

Activations Density 1.879%

words related to gratitude and appreciation

linguistic expressions of approval or positivity

No Comments

No Known Activations