INDEX

Explanations

phrases related to living in a specific location within a community

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

¿½

-0.79

Ĳ

-0.72

dule

-0.70

opoulos

-0.70

casters

-0.69

 tallied

-0.66

 attm

-0.66

 ingred

-0.65

killed

-0.64

STAR

-0.64

POSITIVE LOGITS

 accordance

1.02

 exile

1.00

 tents

0.93

 caves

0.91

 harmony

0.90

 limbo

0.89

 solitude

0.87

 poverty

0.87

 paradise

0.87

 apartments

0.86

Activations Density 0.069%

phrases related to living in a specific location within a community

No Comments

No Known Activations