INDEX

Explanations

terms related to legal and liability concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Söhne

-0.67

 Verein

-0.64

setVerticalGroup

-0.63

közi

-0.63

Hrsg

-0.63

HasAnnotation

-0.61

principalTable

-0.61

弟弟

-0.60

妹妹

-0.60

AddField

-0.59

POSITIVE LOGITS

 Reform

0.64

 spokes

0.59

\|^{

0.58

 oprot

0.57

ers

0.57

 PropertyChanged

0.57

نس

0.56

 ſel

0.56

})));

0.54

นัก

0.54

Activations Density 0.743%

terms related to legal and liability concepts

No Comments

No Known Activations