INDEX

Explanations

concepts related to social and economic disparities

oai_token-act-pair · gpt-4o-mini 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

theless

-0.64

 interchange

-0.63

 captive

-0.61

 infringing

-0.59

 uphill

-0.57

 orally

-0.57

 drunk

-0.56

 deprived

-0.56

 redacted

-0.56

 artificially

-0.56

POSITIVE LOGITS

ctions

1.19

uments

1.15

itions

1.09

ices

1.08

sts

1.06

vals

1.06

ations

1.06

acies

1.06

atures

1.05

ences

1.05

Activations Density 0.273%

concepts related to social and economic disparities

No Comments

No Known Activations