INDEX

Explanations

references to cerebral conditions and significant people associated with them

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

arted

-0.80

alling

-0.77

aries

-0.74

riks

-0.73

nir

-0.71

aret

-0.70

olit

-0.69

unes

-0.67

ministic

-0.67

urated

-0.67

POSITIVE LOGITS

 Shields

0.86

zinski

0.78

swer

0.76

 Springer

0.68

 pals

0.67

issance

0.65

itz

0.63

idges

0.63

 Diet

0.63

auer

0.62

Activations Density 0.004%

references to cerebral conditions and significant people associated with them

No Comments

No Known Activations