INDEX

Explanations

phrases related to official announcements or statements

oai_token-act-pair · gpt-3.5-turbo

pronouns and auxiliary verbs indicating subjects and actions in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 extant

-0.62

 Federation

-0.61

 Parenthood

-0.59

taining

-0.58

vable

-0.56

 Tenth

-0.56

 bachelor

-0.56

Ivy

-0.56

 Bachelor

-0.56

Fine

-0.54

POSITIVE LOGITS

 invariably

1.23

 immediately

1.13

 usually

1.02

 inevitably

1.02

 instantly

0.97

 typically

0.94

 often

0.92

Enlarge

0.90

mediately

0.87

 greeted

0.86

Activations Density 0.236%

phrases related to official announcements or statements

pronouns and auxiliary verbs indicating subjects and actions in sentences

No Comments

No Known Activations