INDEX

Explanations

terms related to legal and criminal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 Houſe

-0.84

 Majefty

-0.80

 Diſ

-0.78

 Anſ

-0.76

 Reſ

-0.76

ſelves

-0.74

IContainer

-0.73

 neceff

-0.72

ſelf

-0.72

AddTagHelper

-0.70

POSITIVE LOGITS

 that

0.57

 where

0.56

of

0.55

 chosen

0.52

 choisis

0.49

 históricos

0.48

 sélectionnés

0.46

 encargado

0.46

 aquilo

0.46

0.45

Activations Density 0.515%

terms related to legal and criminal contexts

No Comments

No Known Activations