INDEX

Explanations

adjectives prefixed with 'un-' that convey negatively perceived characteristics

oai_token-act-pair · gpt-3.5-turbo

words associated with negation or prohibition

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

ulhu

-0.80

wolves

-0.77

Kings

-0.71

Sym

-0.69

aurus

-0.68

*/(

-0.68

 Parish

-0.67

 Beasts

-0.67

 Mercury

-0.65

 Annotations

-0.65

POSITIVE LOGITS

akable

1.05

ached

1.05

ressed

0.91

achable

0.89

romising

0.89

vised

0.88

enced

0.86

asion

0.84

cedented

0.83

ailability

0.82

Activations Density 0.078%

adjectives prefixed with 'un-' that convey negatively perceived characteristics

words associated with negation or prohibition

No Comments

No Known Activations