INDEX

Explanations

programming-related terms and syntax constructs

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

aarrggbb

-0.91

 CreateTagHelper

-0.83

IntoConstraints

-0.79

GeoNames

-0.75

mybatisplus

-0.74

rrggbb

-0.74

UserScript

-0.74

 nakalista

-0.72

CodedInputStream

-0.71

 profusely

-0.69

POSITIVE LOGITS

İstinadlar

0.50

<eos>

0.49

Билгалдахарш

0.43

授

0.42

↵↵

0.41

모

0.41

рем

0.40

tvguidetime

0.39

出版年

0.38

 angeb

0.38

Activations Density 0.225%

programming-related terms and syntax constructs

No Comments

No Known Activations