INDEX

Explanations

phrases related to basketball players

oai_token-act-pair · gpt-3.5-turbo

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UCH

-0.56

Gap

-0.55

 Pixie

-0.54

 Bethlehem

-0.54

 Philipp

-0.54

 Cutter

-0.53

 Patrol

-0.51

 Michelle

-0.50

 Flor

-0.50

 Axel

-0.50

POSITIVE LOGITS

(*

0.92

Thus

0.92

ÂłÂł

0.85

NOTE

0.83

Such

0.83

Therefore

0.82

Furthermore

0.82

Whereas

0.82

Additionally

0.81

Similarly

0.79

Activations Density 1.239%

phrases related to basketball players

No Comments

No Known Activations