INDEX

Explanations

phrases indicating a relationship or interaction between two entities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "and" in combination with other terms that imply relationships or connections

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

 Citation

-0.79

kar

-0.73

quest

-0.72

bard

-0.72

ccording

-0.71

nder

-0.71

 Cosponsors

-0.70

YD

-0.70

spir

-0.68

warn

-0.68

POSITIVE LOGITS

 destiny

0.73

its

0.72

 neighbouring

0.68

 vanquished

0.67

 infinity

0.65

 slavery

0.63

 neighboring

0.63

 rest

0.60

 Great

0.60

 Olympia

0.59

Activations Density 0.124%

phrases indicating a relationship or interaction between two entities

instances of the word "and" in combination with other terms that imply relationships or connections

No Comments

No Known Activations