INDEX

Explanations

references to numerical values or sequences

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

rador

-0.75

 Directorate

-0.66

ossier

-0.64

Materials

-0.64

axter

-0.64

 Tanz

-0.64

 Shroud

-0.64

 Kafka

-0.63

 appre

-0.61

 Despair

-0.61

POSITIVE LOGITS

plates

1.04

plate

0.95

 crunch

0.92

enance

0.91

lessness

0.79

ener

0.79

 plates

0.76

pad

0.72

number

0.72

metry

0.71

Activations Density 0.030%

references to numerical values or sequences

No Comments

No Known Activations