INDEX

Explanations

phrases that describe fame and recognition, particularly in relation to notable individuals or achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Anſ

-0.56

ThroughAttribute

-0.55

iſh

-0.54

 Reſ

-0.53

Eſ

-0.52

provision

-0.51

 Inſ

-0.49

 ModelExpression

-0.48

Jee

-0.47

kháu

-0.46

POSITIVE LOGITS

 famous

1.08

 known

1.02

 KNOWN

0.99

famous

0.92

 Known

0.92

 notorious

0.91

 Famous

0.90

known

0.90

 terkenal

0.89

Famous

0.88

Activations Density 0.194%

phrases that describe fame and recognition, particularly in relation to notable individuals or achievements

No Comments

No Known Activations