INDEX

Explanations

pronominal and possessive pronoun pairings followed by a verb

oai_token-act-pair · gpt-3.5-turbo

phrases indicating subjective opinions and expressions

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

[-

-0.71

andise

-0.70

 Daly

-0.67

ãĤ½

-0.66

ume

-0.64

Mass

-0.62

 clearance

-0.62

 Clicker

-0.62

ãĢĲ

-0.61

BB

-0.61

POSITIVE LOGITS

rosso

0.82

 somew

0.79

 someday

0.78

 misunder

0.73

 wiser

0.70

cheat

0.70

rha

0.70

awaru

0.69

 inadvert

0.67

 swayed

0.65

Activations Density 0.198%

pronominal and possessive pronoun pairings followed by a verb

phrases indicating subjective opinions and expressions

No Comments

No Known Activations