INDEX

Explanations

code-related terms and annotations, particularly those associated with version control and package management

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

 initComponents

-0.82

 oublier

-0.69

-0.65

webpack

-0.63

findpost

-0.61

evaluator

-0.60

 lourdes

-0.60

 nakalista

-0.57

 Chwiliwch

-0.56

:✨

-0.56

POSITIVE LOGITS

CppCodeGen

0.64

)++;

0.62

SetOutput

0.61

 TestBed

0.57

bParam

0.56

addWidget

0.56

êng

0.54

}}/>

0.51

}}}

0.50

).]

0.50

Activations Density 0.039%

code-related terms and annotations, particularly those associated with version control and package management

No Comments

No Known Activations