INDEX

Explanations

the word 'things'

oai_token-act-pair · gpt-3.5-turbo

references to various unspecified topics or subjects

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

geon

-0.85

geons

-0.76

esi

-0.76

oku

-0.74

bern

-0.72

gee

-0.68

iary

-0.67

ICO

-0.65

Mi

-0.65

awar

-0.62

POSITIVE LOGITS

 happening

1.06

 happen

1.04

 happened

0.97

 happens

0.95

 happ

0.83

 transpired

0.76

 occurring

0.76

omething

0.72

 Happ

0.67

 imaginable

0.66

Activations Density 0.044%

the word 'things'

references to various unspecified topics or subjects

No Comments

No Known Activations