INDEX

Explanations

quotations within the text with potential emotional or controversial impact

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 affiliate

-0.79

 Ross

-0.77

 rental

-0.75

 outfielder

-0.73

 matter

-0.73

 rall

-0.72

 grasp

-0.72

 editor

-0.71

 buoy

-0.71

 McKay

-0.70

POSITIVE LOGITS

classic

1.45

false

1.44

true

1.44

pure

1.43

little

1.40

normal

1.40

every

1.38

almost

1.37

double

1.37

nothing

1.35

Activations Density 0.524%

quotations within the text with potential emotional or controversial impact

No Comments

No Known Activations