INDEX

Explanations

references to specific legislation or official authorization related to certain activities

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

enth

-0.98

mania

-0.77

mates

-0.73

 Alto

-0.71

gaard

-0.71

EMS

-0.70

bart

-0.69

Cube

-0.69

 Tiff

-0.68

tsky

-0.67

POSITIVE LOGITS

 authorizing

1.13

 authorization

0.98

 waivers

0.86

 authorize

0.84

authorized

0.83

 paperwork

0.83

 authorized

0.82

 permission

0.81

 appropriations

0.79

 permitting

0.78

Activations Density 0.027%

references to specific legislation or official authorization related to certain activities

No Comments

No Known Activations