INDEX

Explanations

the prefix "pr" followed by a high numerical value, possibly indicating importance or priority

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "pr" likely related to "press" or "public relations."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Dwarf

-0.74

 Wand

-0.73

 Cheong

-0.70

querque

-0.67

liner

-0.64

 EntityItem

-0.64

 Druid

-0.62

STER

-0.61

riad

-0.61

erness

-0.61

POSITIVE LOGITS

udence

1.17

ODUCT

1.05

atche

1.01

ayer

1.00

istine

0.99

inters

0.99

icing

0.99

acking

0.93

ayed

0.92

anded

0.92

Activations Density 0.009%

the prefix "pr" followed by a high numerical value, possibly indicating importance or priority

occurrences of the abbreviation "pr" likely related to "press" or "public relations."

No Comments

No Known Activations