INDEX

Explanations

occurrences of the term "Gre" in various words

oai_token-act-pair · gpt-3.5-turbo

references to the name "Gre" or its variations within different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ¼ãĥĨãĤ£

-0.73

ional

-0.68

DragonMagazine

-0.67

CPC

-0.67

ãĥ¼ãĥ³

-0.66

ividual

-0.66

etheless

-0.65

iasis

-0.65

ãĤ¢ãĥ«

-0.64

Fram

-0.63

POSITIVE LOGITS

yson

1.02

enery

0.99

edy

0.97

ysc

0.91

lev

0.90

aves

0.89

endale

0.89

gg

0.86

ather

0.84

edo

0.84

Activations Density 0.014%

occurrences of the term "Gre" in various words

references to the name "Gre" or its variations within different contexts

No Comments

No Known Activations