INDEX

Explanations

phrases indicating going through a challenging or exhaustive experience

oai_token-act-pair · gpt-3.5-turbo

references to experiences of going through challenges or processes

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

NPR

-0.67

iPhone

-0.66

nai

-0.65

 Nurse

-0.64

 Shine

-0.64

irlfriend

-0.62

POSE

-0.61

Percent

-0.61

AAP

-0.61

ufact

-0.61

POSITIVE LOGITS

 maze

1.03

 labyrinth

1.01

 hoops

0.93

 motions

0.91

 veins

0.90

 ranks

0.81

 stages

0.81

 loops

0.80

 hurdles

0.80

 corridors

0.78

Activations Density 0.276%

phrases indicating going through a challenging or exhaustive experience

references to experiences of going through challenges or processes

No Comments

No Known Activations