INDEX

Explanations

phrases indicating additional information or context

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

ocarditis

-0.64

capp

-0.55

WritableDatabase

-0.55

 inilah

-0.54

Lyrics

-0.53

rature

-0.53

standigheden

-0.52

clairage

-0.52

verhalten

-0.52

 vnnd

-0.51

POSITIVE LOGITS

 besides

1.40

besides

1.34

Besides

1.25

 Besides

1.21

 Além

1.07

Neben

1.06

 além

1.02

 Oltre

1.01

Oltre

1.01

 naast

1.01

Activations Density 0.105%

phrases indicating additional information or context

No Comments

No Known Activations