INDEX

Explanations

evaluative statements with positive connotations

oai_token-act-pair · gpt-3.5-turbo

instances of positive evaluations of individuals or their performances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

selves

-0.73

 attRot

-0.68

),"

-0.68

urers

-0.67

".[

-0.64

.''.

-0.63

 selves

-0.63

 collectively

-0.62

 candidates

-0.61

"—

-0.60

POSITIVE LOGITS

 himself

0.99

 understatement

0.86

 pseudonym

0.79

 blogging

0.78

POV

0.76

 vocals

0.73

 eloqu

0.72

 herself

0.72

his

0.71

 Himself

0.71

Activations Density 1.212%

evaluative statements with positive connotations

instances of positive evaluations of individuals or their performances

No Comments

No Known Activations