INDEX

Explanations

references to legal cases and authors related to those cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Leck

-0.86

 Brunswick

-0.85

SizeF

-0.82

BeginContext

-0.81

parsedMessage

-0.81

ViewFeatures

-0.80

arakhand

-0.80

mbggenerated

-0.80

 Paso

-0.79

Brunswick

-0.79

POSITIVE LOGITS

 Ramirez

0.78

 Josiah

0.75

 äusser

0.73

 Ludlow

0.69

 Salim

0.69

taz

0.69

 Aure

0.69

 Merz

0.69

 Shira

0.68

Aki

0.67

Activations Density 2.187%

references to legal cases and authors related to those cases

No Comments

No Known Activations