INDEX

Explanations

references to pop culture and its various elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

}{*}{}

-0.73

hdashline

-0.65

\}\\

-0.64

 viewType

-0.64

ChildIndex

-0.63

encodeWith

-0.62

digheden

-0.61

 bahagian

-0.60

 opdracht

-0.60

########.

-0.59

POSITIVE LOGITS

pop

2.66

pop

2.44

Pop

2.42

Pop

2.34

POP

2.22

 pops

2.20

POP

2.08

 popping

1.99

pops

1.93

 popped

1.89

Activations Density 0.026%

references to pop culture and its various elements

No Comments

No Known Activations