INDEX

Explanations

words related to complex and intricate systems or problems

oai_token-act-pair · gpt-3.5-turbo

references to complexity in various contexts

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

 Citizens

-0.68

endar

-0.63

amina

-0.62

vil

-0.60

unes

-0.59

 millennium

-0.58

Ķ

-0.58

direct

-0.57

rine

-0.57

inel

-0.57

POSITIVE LOGITS

 complexity

1.05

 complexities

0.87

 proble

0.87

 complicate

0.83

mble

0.83

 cumbers

0.81

iness

0.77

iveness

0.77

 nuance

0.76

layer

0.76

Activations Density 0.010%

words related to complex and intricate systems or problems

references to complexity in various contexts

No Comments

No Known Activations