INDEX

Explanations

species names and classifications, particularly in a biological taxonomy context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

tpu

-0.59

])));

-0.54

psum

-0.53

rawdź

-0.52

setof

-0.51

wade

-0.48

 kicking

-0.47

lyte

-0.46

iettivo

-0.46

 surla

-0.45

POSITIVE LOGITS

 quelcon

0.71

 vestiti

0.67

 enfans

0.64

 prochaines

0.64

 vieill

0.64

 feroit

0.62

 gantung

0.59

 figliu

0.59

 perdita

0.59

 démocr

0.59

Activations Density 0.455%

species names and classifications, particularly in a biological taxonomy context

No Comments

No Known Activations