INDEX

Explanations

references to legal terms and proceedings

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

Follows pronouns

np_acts-logits-general · gemini-2.0-flash

this We that her

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

<bos>

-1.02

kos

-0.36

jo

-0.36

ρυ

-0.36

Ã

-0.35

</tr>

-0.35

úb

-0.35

нен

-0.35

ind

-0.34

 queſta

-0.34

POSITIVE LOGITS

^(@)

0.44

drawal

0.37

>\<^

0.35

[],

0.34

csolódó

0.34

 Theſe

0.33

pecially

0.32

ViewImports

0.32

ideration

0.31

^(@

0.31

Activations Density 39.729%

references to legal terms and proceedings

Follows pronouns

this We that her

No Comments

No Known Activations