INDEX

Explanations

phrases related to improvement or understanding in various contexts

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the enhancement or improvement of understanding

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

heter

-0.66

mad

-0.64

ername

-0.63

note

-0.63

NetMessage

-0.63

 Straw

-0.63

HO

-0.63

itto

-0.61

asma

-0.61

 Dresden

-0.60

POSITIVE LOGITS

 acquainted

0.79

 contextual

0.78

anced

0.77

 understanding

0.77

 leverage

0.75

 suited

0.74

 entreprene

0.74

 transparency

0.74

initions

0.74

 than

0.73

Activations Density 0.055%

phrases related to improvement or understanding in various contexts

phrases emphasizing the enhancement or improvement of understanding

No Comments

No Known Activations