INDEX

Explanations

names of places or geographical locations

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

arers

-0.85

apple

-0.84

glers

-0.84

ebook

-0.77

isite

-0.76

holding

-0.75

iners

-0.75

ocument

-0.74

lance

-0.73

onies

-0.72

POSITIVE LOGITS

Kab

0.92

Benz

0.77

Kaz

0.75

 Kats

0.74

Zen

0.74

henko

0.74

ovych

0.74

Dim

0.73

 Dortmund

0.73

Kon

0.73

Activations Density 0.024%

names of places or geographical locations

No Comments

No Known Activations