INDEX

Explanations

terms related to software functionality and error messages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 initComponents

-0.87

tvguidetime

-0.79

AnimationsModule

-0.74

reportWebVitals

-0.66

 NgModule

-0.66

urlpatterns

-0.65

InstanceState

-0.64

 also

-0.63

 مشين

-0.62

__':

-0.61

POSITIVE LOGITS

其

0.84

 oreilles

0.72

它的

0.71

 plufieurs

0.69

其中的

0.66

自己的

0.66

 étoient

0.65

 feroit

0.64

某

0.64

 médec

0.63

Activations Density 0.023%

terms related to software functionality and error messages

No Comments

No Known Activations