INDEX

Explanations

keywords related to museums and exhibitions

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

Data Type

torch.float32

Hook Point

blocks.8.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

 endeav

-0.73

 reluct

-0.71

 frontline

-0.70

 communicating

-0.69

 administr

-0.69

 communication

-0.69

cffff

-0.69

 opting

-0.68

 relying

-0.67

 determination

-0.66

POSITIVE LOGITS

favorite

1.13

Posted

1.11

Topic

1.06

Topics

1.06

RAW

1.05

Loading

1.04

Rated

1.03

Trivia

0.99

Episode

0.98

âĵĺ

0.98

Activations Density 1.351%

keywords related to museums and exhibitions

No Comments

No Known Activations