INDEX

Explanations

names of organizations and products, particularly in the film and entertainment industry

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

-0.60

 compr

-0.56

[];

-0.54

 =====

-0.54

gra

-0.53

 guiActiveUn

-0.52

soever

-0.51

 Instr

-0.50

"<

-0.50

 bene

-0.50

POSITIVE LOGITS

utenberg

0.67

ropolis

0.59

usha

0.57

ento

0.57

riter

0.57

talk

0.57

tymology

0.56

sin

0.56

actor

0.54

sterdam

0.54

Activations Density 0.252%

names of organizations and products, particularly in the film and entertainment industry

No Comments

No Known Activations