INDEX

Explanations

terms related to legal or formal proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 désolés

-0.65

AccessorTable

-0.63

ographiques

-0.61

 termica

-0.59

úgó

-0.57

topus

-0.57

 économies

-0.56

 Rother

-0.55

 législation

-0.55

 recargable

-0.55

POSITIVE LOGITS

ances

1.24

ance

1.21

ence

1.05

ANCE

1.04

anced

0.96

 ance

0.94

nce

0.93

ANCES

0.93

rance

0.87

ancing

0.87

Activations Density 0.250%

terms related to legal or formal proceedings

No Comments

No Known Activations