INDEX

Explanations

proper nouns, in particular names of people or places

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 eleph

-0.85

ccording

-0.84

CLASSIFIED

-0.76

 laun

-0.74

 behavi

-0.74

Þ

-0.72

 pione

-0.70

 tremend

-0.70

Reloaded

-0.70

 conflic

-0.69

POSITIVE LOGITS

len

0.93

kowski

0.91

eson

0.91

zon

0.89

ley

0.87

son

0.86

axis

0.85

idge

0.85

enson

0.84

ridge

0.84

Activations Density 0.146%

proper nouns, in particular names of people or places

proper nouns, specifically names of people

No Comments

No Known Activations