INDEX

Explanations

references to a location or venue

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

IGHTS

-0.85

soever

-0.81

 toget

-0.73

STEM

-0.73

terday

-0.71

pta

-0.70

KER

-0.69

 sund

-0.69

OWS

-0.68

IAS

-0.68

POSITIVE LOGITS

folio

1.51

rait

1.48

folios

1.46

raits

1.42

ugal

1.09

eur

1.00

ray

0.95

ions

0.90

 Canaveral

0.90

rehens

0.85

Activations Density 0.008%

references to a location or venue

No Comments

No Known Activations