INDEX

Explanations

language that emphasizes complexity and detailed descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

NameValuePair

-0.50

xus

-0.50

ijų

-0.48

rarr

-0.47

 mergeFrom

-0.47

রণ

-0.46

(!_

-0.46

Ont

-0.46

(!_

-0.46

primary

-0.45

POSITIVE LOGITS

 phenomenon

0.85

 genre

0.80

 phénomène

0.72

 topic

0.68

 fenomeno

0.67



0.67

expandindo

0.65

Glej

0.64

 process

0.64

 concept

0.64

Activations Density 0.388%

language that emphasizes complexity and detailed descriptions

No Comments

No Known Activations