INDEX

Explanations

instances of the word "jump" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

↵↵

-0.58

<eos>

-0.54

But

-0.48

</i>

-0.48

↵

-0.47

 fondi

-0.47

-0.46

olato

-0.46

 fondos

-0.46

Sprintf

-0.45

POSITIVE LOGITS

 jump

1.72

 jumps

1.69

 Jump

1.62

 JUMP

1.59

jump

1.56

 Leap

1.54

 jumped

1.53

 jumping

1.50

Jumping

1.49

 leap

1.48

Activations Density 0.085%

instances of the word "jump" and its variations in various contexts

No Comments

No Known Activations