INDEX

Explanations

references to characters or names like "Bilal" in a narrative context

oai_token-act-pair · gpt-3.5-turbo 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

chnology

-0.70

æĸ¹

-0.63

 Crus

-0.63

 Izan

-0.63

 Martial

-0.62

 Families

-0.61

WAR

-0.60

REAM

-0.59

 Surviv

-0.59

ICES

-0.59

POSITIVE LOGITS

gewater

1.33

isi

1.10

ibi

0.95

ascus

0.94

ittle

0.93

boa

0.88

bil

0.88

ibr

0.87

idian

0.87

ison

0.87

Activations Density 0.014%

references to characters or names like "Bilal" in a narrative context

No Comments

No Known Activations