INDEX

Explanations

phrases encouraging action or behavior

oai_token-act-pair · gpt-3.5-turbo

pronouns that indicate actions aimed at encouraging or motivating others

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bourg

-0.56

 artif

-0.56

 Siege

-0.55

 overlap

-0.52

 illumination

-0.51

 backdrop

-0.51

FACE

-0.51

 coincidence

-0.50

ording

-0.50

 haunt

-0.50

POSITIVE LOGITS

 toward

1.16

 into

1.14

 towards

1.11

to

1.08

into

1.02

 onward

0.97

 thereto

0.97

 Into

0.92

 onto

0.91

 onwards

0.85

Activations Density 0.277%

phrases encouraging action or behavior

pronouns that indicate actions aimed at encouraging or motivating others

No Comments

No Known Activations