INDEX

Explanations

words or phrases indicating additional information or similarities

oai_token-act-pair · gpt-3.5-turbo

the word "also" and its various usages in different contexts

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

ASE

-0.67

UGE

-0.66

 Weaver

-0.65

agus

-0.63

 Essence

-0.63

 Banner

-0.62

 Closing

-0.61

 Discovery

-0.61

Fine

-0.61

crow

-0.61

POSITIVE LOGITS

 contributed

0.87

 includes

0.85

 includ

0.84

 referred

0.81

 applies

0.80

 participated

0.79

 benefited

0.79

 incorporates

0.79

 included

0.77

 qualifies

0.76

Activations Density 0.114%

words or phrases indicating additional information or similarities

the word "also" and its various usages in different contexts

No Comments

No Known Activations