INDEX

Explanations

phrases related to people's qualities and actions, particularly focusing on attributes like vision, decision-making, attitude, readiness, and communication

oai_token-act-pair · gpt-3.5-turbo

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ´ãĥ³

-0.90

 è£ıè

-0.72

 Alas

-0.72

DAY

-0.69

 Partial

-0.67

 Warrant

-0.66

 Amid

-0.63

-0.60

 Additional

-0.60

?????-

-0.59

POSITIVE LOGITS

1.17

'll

1.12

 definitely

1.10

zbollah

1.08

 really

1.06

're

1.05

ain

1.05

 basically

1.04

 gotta

1.03

 obviously

1.03

Activations Density 0.223%

phrases related to people's qualities and actions, particularly focusing on attributes like vision, decision-making, attitude, readiness, and communication

No Comments

No Known Activations