INDEX

Explanations

phrases indicating a state of being or existence

oai_token-act-pair · gpt-3.5-turbo

the verb "be" in various forms and 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

edIn

-0.73

perty

-0.69

 prest

-0.67

 Kurd

-0.66

 srfAttach

-0.66

 Seym

-0.65

osate

-0.65

 Azerb

-0.64

Tokens

-0.62

uyomi

-0.62

POSITIVE LOGITS

eps

0.72

heading

0.68

ams

0.66

CLUD

0.64

cloud

0.64

ech

0.64

wolves

0.63

vo

0.62

erc

0.62

vel

0.61

Activations Density 0.037%

phrases indicating a state of being or existence

the verb "be" in various forms and contexts

No Comments

No Known Activations