INDEX

Explanations

phrases that intensify a statement by emphasizing the literal truth of a situation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "literally" to emphasize statements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ies

-0.84

icipated

-0.78

tein

-0.73

ongyang

-0.70

winner

-0.68

ramid

-0.67

alez

-0.67

anim

-0.66

sonian

-0.64

rial

-0.64

POSITIVE LOGITS

 literally

0.72

Ń·

0.71

terday

0.71

ength

0.70

 Literally

0.69

zona

0.67

literally

0.67

ãĤ§

0.65

qqa

0.64

 kidding

0.63

Activations Density 0.006%

phrases that intensify a statement by emphasizing the literal truth of a situation

instances of the word "literally" to emphasize statements

No Comments

No Known Activations