INDEX

Explanations

proper nouns and terms that represent entities or classifications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DockStyle

-0.67

kään

-0.63

sification

-0.61

enumi

-0.59

 становника

-0.59

ydi

-0.57

sified

-0.56

ler

-0.56

 getItemId

-0.54

|}{}

-0.52

POSITIVE LOGITS

dak

0.54

ın

0.52

 *)__

0.51

da

0.48

Browsable

0.48

latego

0.47

AddTagHelper

0.47

ękuję

0.46

dada

0.46

IMPORTED

0.46

Activations Density 0.108%

proper nouns and terms that represent entities or classifications

No Comments

No Known Activations