INDEX

Explanations

terms related to histological and pathological examination findings

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

Histological descriptions

np_acts-logits-general · gemini-2.0-flash

histological changes and pathology

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 houſe

-0.72

 ſche

-0.68

 purpoſe

-0.67

 propOrder

-0.64

 pleaſure

-0.61

enumi

-0.61

PhysRev

-0.61

 repatriation

-0.60

 nephe

-0.60

 ſtand

-0.60

POSITIVE LOGITS

 Pathology

0.59

 wireType

0.59

 pathology

0.57

 Pathol

0.56

 dense

0.54

 Hist

0.53

 hyperplasia

0.53

testify

0.53

 hist

0.52

Histology

0.51

Activations Density 1.708%

terms related to histological and pathological examination findings

Histological descriptions

histological changes and pathology

No Comments

No Known Activations