INDEX

Explanations

import statements and class definitions in code

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

lieb

-0.52

dr

-0.50

 Spisak

-0.45

loch

-0.45

TagMode

-0.44

×</

-0.44

 terletak

-0.43

XXXXX

-0.43

hitheater

-0.43

POSITIVE LOGITS

Personensuche

0.70

httphttps

0.67

/**

0.66

хьтан

0.61

ViewFeatures

0.59

import

0.58

)))));

0.57

public

0.57

 rowspan

0.56

%)$

0.56

Activations Density 0.021%

import statements and class definitions in code

No Comments

No Known Activations