INDEX

Explanations

political terms and affiliations

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oval

-0.60

achine

-0.57

eco

-0.55

 Pacific

-0.55

 retro

-0.54

 reluct

-0.54

 revenge

-0.53

FI

-0.53

 vengeance

-0.53

 unbeliev

-0.51

POSITIVE LOGITS

().

0.83

 attRot

0.79

 counterparts

0.78

 anymore

0.77

*.

0.76

!.

0.73

":[

0.73

.'

0.71

 existed

0.71

Activations Density 0.268%

political terms and affiliations

No Comments

No Known Activations