INDEX

Explanations

terms related to biology, specifically focusing on research areas like physiology, pathology, and toxicology

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

principalColumn

-0.71

RenderAtEndOf

-0.71

 espir

-0.71

Искәрмәләр

-0.65

AsStream

-0.64

եռ

-0.61

providedIn

-0.61

 otomatig

-0.60

 dây

-0.59

ähig

-0.59

POSITIVE LOGITS

 physiology

0.88

 geology

0.87

iology

0.85

 anatomy

0.82

 Geology

0.81

geography

0.80

ology

0.76

 geography

0.76

 biology

0.76

 hydrology

0.75

Activations Density 0.452%

terms related to biology, specifically focusing on research areas like physiology, pathology, and toxicology

No Comments

No Known Activations