INDEX

Explanations

specialized formatting or token markers in texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

-0.79

-0.63

-0.60

-0.59

we

-0.58

-0.55

you

-0.53

–

-0.51

</strong>

-0.50

POSITIVE LOGITS

 nakalista

1.39

 initComponents

1.06

WithIOException

1.02

 ་་

1.01

 ―――――

0.99

 itſelf

0.97

addCriterion

0.96

ItemBackground

0.94

 myſelf

0.94

 pleaſure

0.94

Activations Density 0.219%

specialized formatting or token markers in texts

No Comments

No Known Activations