INDEX

Explanations

names of individuals and their actions or situations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

endif

-0.77

Repeat

-0.70

soType

-0.65

Ide

-0.65

problem

-0.64

orians

-0.62

orian

-0.61

âĶģ

-0.57

history

-0.57

 Amen

-0.57

POSITIVE LOGITS

 realised

1.01

 arrived

0.99

 ventured

0.99

'd

0.97

 became

0.96

 joined

0.96

 confronted

0.95

 transitioned

0.92

 began

0.92

 realized

0.90

Activations Density 0.118%

names of individuals and their actions or situations

No Comments

No Known Activations