INDEX

Explanations

places and political entities in a document

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

 Dover

-0.74

eatures

-0.70

 Stain

-0.70

gradient

-0.70

olid

-0.59

ãĥĥãĥĪ

-0.59

 Simpl

-0.59

Tags

-0.58

uesday

-0.57

inse

-0.56

POSITIVE LOGITS

who

0.97

who

0.95

 whom

0.93

 swear

0.77

whose

0.75

 willing

0.73

 eaves

0.72

 interested

0.71

hari

0.69

untled

0.69

Activations Density 0.330%

places and political entities in a document

No Comments

No Known Activations