INDEX

Explanations

phrases related to modding in software development

oai_token-act-pair · gpt-3.5-turbo

references to modifications or mods in gaming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

lihood

-0.76

 Bucc

-0.75

velt

-0.70

 Baptist

-0.70

 Winds

-0.69

ï¸

-0.68

 Apost

-0.68

 Beir

-0.67

 Quarterly

-0.66

 Hawks

-0.65

POSITIVE LOGITS

icum

1.25

ifiable

1.21

elled

1.15

ding

1.14

ulo

1.08

ifies

1.03

ded

1.02

ifications

1.00

ulators

0.98

der

0.93

Activations Density 0.009%

phrases related to modding in software development

references to modifications or mods in gaming contexts

No Comments

No Known Activations