INDEX

Explanations

occurrences of the preposition 'in' and its contextual relevance

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

âĿ

-0.70

-0.66

resh

-0.63

awei

-0.62

 Unsure

-0.61

ILLE

-0.59

Ľ

-0.58

enance

-0.57

 lodged

-0.55

 encount

-0.55

POSITIVE LOGITS

 spite

1.24

 accordance

1.18

 addition

1.16

cluding

1.14

clus

1.12

 conjunction

1.12

clud

1.11

cluded

1.05

 contrast

1.05

 lieu

1.01

Activations Density 0.066%

occurrences of the preposition 'in' and its contextual relevance

No Comments

No Known Activations