INDEX

Explanations

phrases related to accuracy or precision

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to various forms of "literacy" or "ability."

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

izen

-0.76

wagen

-0.70

eming

-0.70

Mars

-0.69

animous

-0.68

sets

-0.67

ers

-0.67

ractive

-0.65

sen

-0.64

STON

-0.62

POSITIVE LOGITS

cling

0.88

encies

0.82

chin

0.82

rics

0.81

clinton

0.79

cles

0.77

acies

0.73

ritic

0.73

combe

0.71

ency

0.71

Activations Density 0.060%

phrases related to accuracy or precision

terms and phrases related to various forms of "literacy" or "ability."

No Comments

No Known Activations