INDEX

Explanations

references to various publication formats or sources

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

 sleep

-0.77

 jump

-0.74

 nightly

-0.72

 swell

-0.72

ton

-0.71

 comparisons

-0.71

 entitle

-0.70

 killer

-0.70

 jumping

-0.69

 gross

-0.69

POSITIVE LOGITS

formerly

1.30

emphasis

1.23

sic

1.23

Attach

1.19

both

1.17

see

1.14

1.13

...)

1.12

1.11

1.10

Activations Density 0.070%

references to various publication formats or sources

No Comments

No Known Activations