INDEX

Explanations

positively valenced adjectives

oai_token-act-pair · gpt-3.5-turbo

instances of the word "generous" and related terms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Downloadha

-0.85

nuclear

-0.76

enf

-0.71

iph

-0.70

olith

-0.69

 Rite

-0.69

agate

-0.68

urg

-0.68

war

-0.67

 Chern

-0.67

POSITIVE LOGITS

 generous

1.21

 generously

0.94

 gifts

0.91

 enough

0.90

 amounts

0.89

 invitations

0.88

 generosity

0.86

 donor

0.84

 donors

0.82

 benef

0.81

Activations Density 0.012%

positively valenced adjectives

instances of the word "generous" and related terms

No Comments

No Known Activations