INDEX

Explanations

references to governmental or organizational bodies

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

Ïī

-0.65

elfth

-0.63

oulos

-0.60

enegger

-0.59

essage

-0.57

oscope

-0.57

$.

-0.57

atever

-0.56

ãĥ¼ãĥĨ

-0.54

yz

-0.54

POSITIVE LOGITS

 officials

0.90

 approves

0.76

wide

0.72

 Appro

0.70

 Officials

0.69

 announces

0.69

 planners

0.68

 insiders

0.68

 chiefs

0.67

goers

0.66

Activations Density 0.134%

references to governmental or organizational bodies

No Comments

No Known Activations