INDEX

Explanations

repeated mentions of the word "his."

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

IVERS

-0.80

 largeDownload

-0.77

itect

-0.70

Accept

-0.69

endif

-0.69

Grid

-0.68

ocument

-0.63

spir

-0.63

Load

-0.63

Textures

-0.63

POSITIVE LOGITS

own

1.42

panic

1.25

 wife

1.23

 father

1.05

 colleague

1.04

 nephew

1.00

 fian

1.00

son

0.96

 colleagues

0.96

 daughter

0.95

Activations Density 0.214%

repeated mentions of the word "his."

No Comments

No Known Activations