INDEX

Explanations

numeric values representing an increase or rise

oai_token-act-pair · gpt-3.5-turbo

instances of the word "risen" and its variations, indicating increases or growth

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ner

-0.77

Doc

-0.65

 Crit

-0.65

DB

-0.63

hand

-0.61

Doc

-0.61

 Koen

-0.61

Random

-0.60

db

-0.59

 Gene

-0.59

POSITIVE LOGITS

 risen

3.47

 rise

1.74

 fallen

1.68

 ascended

1.64

 arisen

1.59

 rose

1.55

 rises

1.52

 rising

1.50

rising

1.49

 soared

1.40

Activations Density 0.012%

numeric values representing an increase or rise

instances of the word "risen" and its variations, indicating increases or growth

No Comments

No Known Activations