INDEX

Explanations

proper nouns related to people and organizations

oai_token-act-pair · gpt-3.5-turbo

names of people, organizations, and entities associated with numerical data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

etimes

-0.69

âĶĢâĶĢâĶĢâĶĢ

-0.67

yond

-0.66

ãĥĥãĤ¯

-0.66

ãĥ¬

-0.64

soType

-0.63

Redd

-0.62

$.

-0.62

 eternity

-0.62

ãĤ¤ãĥĪ

-0.59

POSITIVE LOGITS

 meanwhile

1.31

 fared

1.07

 likewise

1.06

 dominates

0.98

 also

0.96

 echoed

0.95

 replaced

0.93

 similarly

0.93

 reacted

0.90

 joined

0.90

Activations Density 0.725%

proper nouns related to people and organizations

names of people, organizations, and entities associated with numerical data or statistics

No Comments

No Known Activations