INDEX

Explanations

mentions of mindset and mentality

oai_token-act-pair · gpt-3.5-turbo

concepts related to mindset and mentality

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

drivers

-0.78

idan

-0.73

weather

-0.71

icles

-0.69

oval

-0.68

akov

-0.66

atar

-0.66

adder

-0.66

abet

-0.66

lev

-0.66

POSITIVE LOGITS

 mindset

0.89

 mentality

0.88

 perme

0.86

matic

0.82

 perv

0.79

matically

0.76

 ingrained

0.73

Ħ¢

0.72

 attitude

0.70

 prev

0.67

Activations Density 0.035%

mentions of mindset and mentality

concepts related to mindset and mentality

No Comments

No Known Activations