INDEX

Explanations

phrases and terms related to medical or biological processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 utafitiHapana

-0.71

AddTagHelper

-0.70

 FetchType

-0.65

 protoimpl

-0.63

tanleria

-0.59

oredCriteria

-0.58

kloped

-0.54

DebuggerNonUser

-0.53

CPtr

-0.53

 hefyd

-0.53

POSITIVE LOGITS

 within

3.25

within

3.03

 Within

2.99

Within

2.97

 WITHIN

2.66

 innerhalb

2.19

 binnen

1.96

 dentro

1.82

 inom

1.78

ภายใน

1.64

Activations Density 0.726%

phrases and terms related to medical or biological processes

No Comments

No Known Activations