INDEX

Explanations

terms related to medical and legal terminology, particularly concerning negligence and treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

JspWriter

-0.85

 ExecuteAsync

-0.76

IVEREF

-0.71

 <>",

-0.68

Cyfeiriadau

-0.66

SharedCtor

-0.65

pausal

-0.63

Попис

-0.62

 дописавши

-0.62

 للاسماء

-0.61

POSITIVE LOGITS

ort

0.71

ORT

0.64

orts

0.62

 BoxDecoration

0.61

Cro

0.61

orting

0.58

cro

0.57

 folded

0.55

*/].

0.52

Cro

0.51

Activations Density 2.266%

terms related to medical and legal terminology, particularly concerning negligence and treatments

No Comments

No Known Activations