INDEX

Explanations

phrases indicating a need for improvement or enhancement

oai_token-act-pair · gpt-4o-mini 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

nown

-0.72

azar

-0.70

abal

-0.67

umbered

-0.65

vantage

-0.62

 Associ

-0.62

emies

-0.60

RANT

-0.60

uthor

-0.60

aneously

-0.60

POSITIVE LOGITS

 refres

1.00

 urgently

0.88

 HELP

0.88

 help

0.82

 patience

0.79

 assurances

0.78

 reinforcement

0.77

 clarification

0.75

 assurance

0.74

 luck

0.74

Activations Density 0.150%

phrases indicating a need for improvement or enhancement

No Comments

No Known Activations