INDEX

Explanations

programming and testing related terms within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

ÍTULO

-0.55

ítulo

-0.54

%",

-0.48

elry

-0.48

%',

-0.48

('.',

-0.47

躇

-0.47

 '\\;'

-0.46

"]];

-0.46

told

-0.46

POSITIVE LOGITS

 &___

1.61

->___

1.08

DockStyle

0.98

 unknownFields

0.95

IndentedString

0.89

isSet

0.87

ⓘ

0.86

LookAnd

0.85

 Monfieur

0.82

 Theſe

0.82

Activations Density 0.095%

programming and testing related terms within code

No Comments

No Known Activations