INDEX

Explanations

instances of the word "to."

oai_token-act-pair · gpt-4o-mini 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

interstitial

-0.78

Got

-0.63

holes

-0.63

 varies

-0.58

balls

-0.58

rag

-0.57

 Perspective

-0.56

mentioned

-0.55

pie

-0.55

canon

-0.55

POSITIVE LOGITS

 celebrate

1.23

 relieve

1.17

 commemorate

1.15

 meet

1.14

 receive

1.13

 participate

1.13

 retrieve

1.12

 seek

1.11

 promote

1.10

 partake

1.10

Activations Density 0.131%

instances of the word "to."

No Comments

No Known Activations