INDEX

Explanations

phrases related to introducing or beginning a new era or significant phase

oai_token-act-pair · gpt-3.5-turbo

terms related to transitions or introductions of new eras or movements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

uffy

-0.76

ebin

-0.70

ierrez

-0.70

 guessing

-0.68

 disposition

-0.67

 sore

-0.67

ouf

-0.65

Amount

-0.65

ross

-0.65

 inconsistency

-0.63

POSITIVE LOGITS

 usher

2.58

 herald

2.23

 ushered

2.06

 pioneer

1.96

 inaug

1.88

 pioneered

1.81

 pioneering

1.80

 paving

1.77

 pioneers

1.76

 groundbreaking

1.68

Activations Density 0.031%

phrases related to introducing or beginning a new era or significant phase

terms related to transitions or introductions of new eras or movements

No Comments

No Known Activations