INDEX

Explanations

terms related to psychology and sociology like ideological concepts, social behaviors, and political ideologies

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

srf

-0.71

idth

-0.66

usha

-0.65

ãĥ³ãĤ¸

-0.63

anium

-0.61

akin

-0.61

NK

-0.59

ococ

-0.59

ctors

-0.55

dim

-0.55

POSITIVE LOGITS

 ASAP

0.82

.</

0.78

 firsthand

0.77

.<

0.77

 HuffPost

0.74

 because

0.74

 myself

0.73

 ourselves

0.72

naire

0.72

0.71

Activations Density 0.251%

terms related to psychology and sociology like ideological concepts, social behaviors, and political ideologies

No Comments

No Known Activations