INDEX

Explanations

terms and phrases associated with technical concepts and coding errors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 createState

-0.56

 unknownFields

-0.55

Personendaten

-0.54

[++

-0.51

kmale

-0.50

__':

-0.48

OrBuilder

-0.48

Relevant

-0.47

 acceptez

-0.47

 Then

-0.47

POSITIVE LOGITS

 vyroben

0.74

した場合

0.71

 taken

0.70

 apapun

0.70

 conducted

0.70

 undertaken

0.70

testens

0.69

 Qualquer

0.68

 yapılan

0.67

 obtained

0.67

Activations Density 0.797%

terms and phrases associated with technical concepts and coding errors

No Comments

No Known Activations