INDEX

Explanations

words related to thinking of or considering different ideas or options

oai_token-act-pair · gpt-3.5-turbo

expressions of contemplation or thoughtfulness

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

anger

-0.66

roma

-0.66

cius

-0.64

 Recomm

-0.62

BuyableInstoreAndOnline

-0.61

amar

-0.60

always

-0.59

FBI

-0.58

initely

-0.57

astern

-0.57

POSITIVE LOGITS

 muster

0.93

 satisf

0.86

 coherent

0.74

handle

0.70

 convinc

0.70

 convincing

0.69

 grasp

0.68

successfully

0.68

 adequately

0.67

 plaus

0.65

Activations Density 0.480%

words related to thinking of or considering different ideas or options

expressions of contemplation or thoughtfulness

No Comments

No Known Activations