INDEX

Explanations

keywords related to critiques or reviews

oai_token-act-pair · gpt-3.5-turbo

the word "crit" and its variations, indicating a focus on criticism or critique-related discussions

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

pires

-0.77

Leary

-0.70

noon

-0.70

XT

-0.69

WD

-0.68

orthy

-0.67

UTH

-0.66

velt

-0.64

¶ħ

-0.64

ILY

-0.63

POSITIVE LOGITS

erion

1.46

icism

1.27

ique

1.19

iques

1.13

 Crit

1.03

eria

1.03

iqu

1.00

ically

0.98

osure

0.92

icals

0.89

Activations Density 0.007%

keywords related to critiques or reviews

the word "crit" and its variations, indicating a focus on criticism or critique-related discussions

No Comments

No Known Activations