INDEX

Explanations

terms related to morphology and morbidities

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GenerationType

-0.61

InputTagHelper

-0.60

SpringBootTest

-0.54

BaseType

-0.53

 przód

-0.52

fulness

-0.52

requipa

-0.52

spreis

-0.52

OGUE

-0.52

[]>

-0.51

POSITIVE LOGITS

Mor

1.15

Mor

1.09

mor

0.94

mor

0.92

MOR

0.91

 Morpho

0.82

 Morley

0.77

 morpho

0.73

 morph

0.73

MOR

0.71

Activations Density 0.066%

terms related to morphology and morbidities

No Comments

No Known Activations