INDEX

Explanations

phrases indicating a prominent or superior position, such as "leading" or "premier."

oai_token-act-pair · gpt-3.5-turbo

phrases indicating leadership or prominence in various fields or industries

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

../

-0.80

meyer

-0.75

selage

-0.73

abal

-0.73

 Akin

-0.72

eto

-0.71

iry

-0.70

jad

-0.70

Details

-0.69

PART

-0.68

POSITIVE LOGITS

 innov

1.02

 curated

0.84

 worldwide

0.82

 Encyclopedia

0.80

 fastest

0.80

 benchmark

0.80

 collaborative

0.79

 bestselling

0.78

 trending

0.77

 automotive

0.77

Activations Density 0.177%

phrases indicating a prominent or superior position, such as "leading" or "premier."

phrases indicating leadership or prominence in various fields or industries

No Comments

No Known Activations