INDEX

Explanations

returns in programming code, particularly those related to conditions and values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

otriva

-0.52

'}}>

-0.52

httphttps

-0.51

"}}>

-0.51

subsection

-0.49

%;">

-0.49

 andato

-0.48

who

-0.47

we

-0.47

Razor

-0.47

POSITIVE LOGITS

argout

0.85

__(/*!

0.79

 return

0.76

govina

0.73

uride

0.71

WithIOException

0.71

blossom

0.69

SBATCH

0.68

Portály

0.67

LLAB

0.66

Activations Density 0.072%

returns in programming code, particularly those related to conditions and values

No Comments

No Known Activations