INDEX

Explanations

references to popular TV shows, characters, and their creators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 resourceCulture

-0.71

 AssemblyCulture

-0.68

وفاته

-0.67

falle

-0.65

mybatisplus

-0.64

 nakalista

-0.63

NewUrlParser

-0.62

ictwa

-0.62

mtrl

-0.61

 الرياضيه

-0.60

POSITIVE LOGITS

InSection

0.56

 نف

0.51

 birra

0.48

 premium

0.47

null

0.46

参

0.46

OrNil

0.46

рей

0.45

pod

0.45

duy

0.44

Activations Density 0.585%

references to popular TV shows, characters, and their creators

No Comments

No Known Activations