INDEX

Explanations

legal terminology and references to court cases

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Theſe

-1.14

 Jefus

-1.04

 Monfieur

-1.03

 ſeveral

-1.00

ſelves

-0.97

 itſelf

-0.96

Efq

-0.96

 myſelf

-0.94

 houſe

-0.94

 lenker

-0.94

POSITIVE LOGITS

0.58

-,

0.56

<eos>

0.48

-/

0.47

0.45

0.44

</em>

0.42

0.41

↵↵

0.40

Activations Density 0.266%

legal terminology and references to court cases

No Comments

No Known Activations