INDEX

Explanations

proper nouns or names of people

oai_token-act-pair · gpt-3.5-turbo

references to notable individuals and their actions

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

alys

-0.70

rap

-0.64

ento

-0.63

 itself

-0.62

itiz

-0.62

earcher

-0.61

rina

-0.61

stem

-0.59

duc

-0.57

afety

-0.56

POSITIVE LOGITS

 respectively

1.44

 together

1.28

together

1.14

 Together

1.00

 jointly

0.99

selves

0.94

 respective

0.93

 apiece

0.88

Together

0.88

 mutually

0.88

Activations Density 0.676%

proper nouns or names of people

references to notable individuals and their actions

No Comments

No Known Activations