INDEX

Explanations

keywords related to programming or technical specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

StructEnd

-0.94

Personendaten

-0.91

󠁮

-0.83

তথ্যসূত্র

-0.81

setVerticalGroup

-0.75

 ModelRenderer

-0.74

 виправивши

-0.74

 endblock

-0.74

 initComponents

-0.73

Cordialement

-0.73

POSITIVE LOGITS

 לה

0.64

ta

0.56

Sh

0.56

Ber

0.55

jā

0.55

chlag

0.54

ל

0.54

 dead

0.53

Sh

0.52

Ta

0.51

Activations Density 0.076%

keywords related to programming or technical specifications

No Comments

No Known Activations