INDEX

Explanations

references to grants or funding

oai_token-act-pair · gpt-3.5-turbo

terms related to grants and funding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Ple

-0.67

 Atmosp

-0.66

stals

-0.66

 Sins

-0.62

Clean

-0.61

Appearance

-0.61

 Plain

-0.61

Face

-0.61

Bie

-0.60

âĸł

-0.60

POSITIVE LOGITS

 grant

0.97

ees

0.93

 awarded

0.87

funded

0.82

 grants

0.82

 funding

0.80

 recipients

0.79

 renewal

0.78

 amnesty

0.78

 granted

0.78

Activations Density 0.025%

references to grants or funding

terms related to grants and funding

No Comments

No Known Activations