INDEX

Explanations

names of organizations or associations

oai_token-act-pair · gpt-3.5-turbo

proper nouns and organizations related to various industries and sectors

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.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

 bunk

-0.83

 fodder

-0.77

 sneakers

-0.76

 vocals

-0.70

 balloons

-0.70

 dishes

-0.69

 pets

-0.69

 hiking

-0.69

 tofu

-0.69

 headphones

-0.69

POSITIVE LOGITS

 Association

1.82

 Improvement

1.51

 Associ

1.37

 Owners

1.33

 Manufact

1.31

 Federation

1.30

 Advisory

1.28

 Society

1.27

 Institute

1.25

 Regulatory

1.25

Activations Density 0.307%

names of organizations or associations

proper nouns and organizations related to various industries and sectors

No Comments

No Known Activations