INDEX

Explanations

dialogue within quotations

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

 pole

-0.81

 characterized

-0.79

 targeted

-0.78

 valued

-0.78

 adjud

-0.74

 endeav

-0.73

 undersc

-0.73

 frontline

-0.73

 litter

-0.72

 innov

-0.72

POSITIVE LOGITS

Yeah

1.60

Hmm

1.58

Oh

1.56

Huh

1.55

Hey

1.53

Yes

1.50

Okay

1.48

Alright

1.48

Uh

1.47

Fuck

1.46

Activations Density 0.082%

dialogue within quotations

No Comments

No Known Activations

dialogue within quotations

No Comments

No Known Activations