INDEX

Explanations

imperative phrases urging action

oai_token-act-pair · gpt-3.5-turbo

references to encouragement and participation in activities or projects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ranch

-0.72

printf

-0.67

olver

-0.66

acea

-0.63

cross

-0.60

pac

-0.60

iatric

-0.59

 tragically

-0.59

collect

-0.59

ols

-0.58

POSITIVE LOGITS

 yourselves

1.12

 Yourself

1.07

 yourself

0.94

 thou

0.72

 References

0.71

 Skies

0.71

!:

0.71

 Citation

0.71

 Pricing

0.67

 Explain

0.67

Activations Density 0.283%

imperative phrases urging action

references to encouragement and participation in activities or projects

No Comments

No Known Activations