INDEX

Explanations

phrases related to the concept of "integrity"

oai_token-act-pair · gpt-3.5-turbo

phrases indicating integrity or stability

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

rev

-0.83

orthy

-0.80

utan

-0.77

KK

-0.74

aire

-0.71

arro

-0.68

traumatic

-0.68

rina

-0.68

ESA

-0.68

irs

-0.67

POSITIVE LOGITS

 Nanto

0.78

 existing

0.72

our

0.67

 these

0.65

 diction

0.64

 light

0.63

 incoming

0.62

 manner

0.62

 those

0.62

 their

0.61

Activations Density 0.186%

phrases related to the concept of "integrity"

phrases indicating integrity or stability

No Comments

No Known Activations