INDEX

Explanations

phrases related to personal reflections or opinions

oai_token-act-pair · gpt-3.5-turbo

references to personal choices and their significance

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

 Congo

-0.77

 Camer

-0.74

 Venezuel

-0.71

 Tourism

-0.69

 Angola

-0.68

 Beirut

-0.67

 Algeria

-0.65

 Telephone

-0.65

 Guatemala

-0.64

 Hollande

-0.64

POSITIVE LOGITS

 explanatory

0.92

 respective

0.89

 overarching

0.87

 explan

0.84

 conclusions

0.79

 informative

0.79

 meta

0.78

 methodological

0.77

 respectively

0.77

 assumptions

0.76

Activations Density 1.254%

phrases related to personal reflections or opinions

references to personal choices and their significance

No Comments

No Known Activations